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

    Neuronpedia

    INDEX
    Explanations

    expressions related to reactions or emotional responses

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the word "when" in contexts indicating timing or conditions

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

    "when", "whenever", "if", "after"

    Explanation Uploaded by User
    New Auto-Interp
    Negative Logits
    sonian
    -0.93
    arnaev
    -0.90
    illary
    -0.83
    ormal
    -0.74
    antage
    -0.74
    ictionary
    -0.73
    olars
    -0.73
    hazard
    -0.73
    Stew
    -0.72
    abal
    -0.71
    POSITIVE LOGITS
     startled
    0.86
    soever
    0.84
     witnessing
    0.75
     unsuccessful
    0.72
     uttered
    0.70
     recalling
    0.70
     bitten
    0.67
     hearing
    0.67
     passers
    0.65
     greeting
    0.64
    Act Density 0.193%

    No Known Activations