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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns followed by a verb indicating a specific action

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe the subject "it" and its various states or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fernand
    -0.69
    eon
    -0.69
    anamo
    -0.69
    reon
    -0.68
    etheless
    -0.65
    ELD
    -0.62
    Es
    -0.62
    Ts
    -0.62
     eleph
    -0.59
    profits
    -0.59
    POSITIVE LOGITS
     disadvant
    0.66
    liest
    0.62
     joke
    0.61
    put
    0.60
     rel
    0.59
    GUI
    0.59
    ifice
    0.58
     toast
    0.57
    uni
    0.57
    lier
    0.57
    Act Density 0.164%

    No Known Activations