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

    Neuronpedia

    INDEX
    Explanations

    the word "straight" in various contexts and forms

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

    "Straight" followed by direction-related words

    np_acts-logits-general · gemini-2.0-flash

    straight forward or direct

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    awaiter
    -0.59
    abestanden
    -0.58
    tagHelperRunner
    -0.57
    IElement
    -0.57
    obium
    -0.56
    MessageOf
    -0.54
    __;
    -0.54
     ApiException
    -0.53
    :✨
    -0.53
    URBANA
    -0.53
    POSITIVE LOGITS
    forward
    1.02
    jacket
    0.91
    DeleteBehavior
    0.81
    jacke
    0.81
    eners
    0.80
    FORWARD
    0.77
    laced
    0.76
     otomatig
    0.74
    ening
    0.71
    ener
    0.68
    Act Density 0.093%

    No Known Activations