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

    Neuronpedia

    INDEX
    Explanations

    phrases related to numbers or mathematical expressions

    oai_token-act-pair · gpt-3.5-turbo

    special characters or punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ally
    -0.68
    doors
    -0.65
     disadvant
    -0.61
    enhagen
    -0.60
     exha
    -0.59
     toes
    -0.58
     blasphemy
    -0.58
     vulner
    -0.58
     generals
    -0.58
    iani
    -0.57
    POSITIVE LOGITS
    actionDate
    0.74
    mosp
    0.73
     partName
    0.69
     Psy
    0.67
    taboola
    0.65
    nee
    0.64
     ][
    0.63
    hov
    0.63
    ead
    0.59
    CLUS
    0.58
    Act Density 0.062%

    No Known Activations