Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    instances of the word "look" and its variations, indicating a focus on searching or observing actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "look" followed by spatial prepositions

    np_acts-logits-general · gemini-2.0-flash

    look followed by prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GenerationType
    -0.70
    })$}
    -0.70
    contentLoaded
    -0.69
     externi
    -0.66
    /**
    -0.66
    elemField
    -0.65
    MessageTagHelper
    -0.65
    antMatchers
    -0.64
    vician
    -0.64
     fallu
    -0.61
    POSITIVE LOGITS
     through
    0.85
     into
    0.69
     around
    0.60
     melalui
    0.56
     igenom
    0.54
     THROUGH
    0.52
     over
    0.50
     past
    0.49
     thru
    0.49
     review
    0.48
    Act Density 0.112%

    No Known Activations