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

    Neuronpedia

    INDEX
    Explanations

    phrases related to identity verification and personal documentation

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

    followed by forms of "suru" (to do)

    np_acts-logits-general · gemini-2.0-flash

    actions and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ாம்
    -0.66
    yorsunuz
    -0.63
    νονται
    -0.62
    ிறது
    -0.59
    yordu
    -0.59
     Chinatown
    -0.59
    Personendaten
    -0.56
    Demografie
    -0.56
    licet
    -0.56
    下载附件
    -0.55
    POSITIVE LOGITS
     typelib
    0.65
     EconPapers
    0.55
     done
    0.53
    ureusement
    0.48
     able
    0.47
    ing
    0.47
     történ
    0.46
     autorytatywna
    0.45
    able
    0.45
    saraba
    0.45
    Act Density 0.043%

    No Known Activations