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

    Neuronpedia

    INDEX
    Explanations

    phrases related to filling out forms

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the action of filling in forms or applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     DRAG
    -0.81
    edu
    -0.76
     Pigs
    -0.71
     Rhythm
    -0.71
    oleon
    -0.68
    MQ
    -0.66
     Seas
    -0.65
    -+
    -0.64
    WS
    -0.63
    iannopoulos
    -0.62
    POSITIVE LOGITS
     coffers
    0.71
    auga
    0.66
    emort
    0.65
    verson
    0.65
    Case
    0.64
    estine
    0.64
    phabet
    0.64
    fill
    0.63
    ridge
    0.63
     Lauder
    0.62
    Act Density 0.038%

    No Known Activations