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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a specific sequence or arrangement of actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases beginning with "in order to" that imply purpose or intention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inav
    -0.65
    raped
    -0.64
    eworld
    -0.59
    erno
    -0.56
    vas
    -0.56
    oos
    -0.54
    etheless
    -0.54
    ahime
    -0.53
    bour
    -0.53
    kan
    -0.53
    POSITIVE LOGITS
     to
    1.11
     thereto
    0.86
    to
    0.70
    ":"/
    0.65
    awaru
    0.62
    İ
    0.61
    To
    0.61
     To
    0.60
     Osw
    0.60
    llor
    0.60
    Act Density 0.026%

    No Known Activations