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

    Neuronpedia

    INDEX
    Explanations

    phrases that encourage acquiring additional information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     MURRAY
    -0.54
    ättä
    -0.53
     put
    -0.52
    ar
    -0.51
     Schmel
    -0.51
     output
    -0.51
     OUTPUT
    -0.50
     useDispatch
    -0.50
     BIBSYS
    -0.50
    HttpDelete
    -0.49
    POSITIVE LOGITS
     متعلقه
    0.92
    __(/*!
    0.90
     how
    0.83
    Conheça
    0.82
    UpInside
    0.73
     فريبيس
    0.72
    aimana
    0.71
    ValueStyle
    0.71
     hvordan
    0.69
     насељу
    0.69
    Act Density 0.171%

    No Known Activations