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

    Neuronpedia

    INDEX
    Explanations

    colloquial phrases or contractions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illance
    -0.15
    ubu
    -0.15
    thon
    -0.15
    oku
    -0.15
    amı
    -0.14
    ogue
    -0.14
    oft
    -0.14
    shima
    -0.14
    ToSelector
    -0.13
    edb
    -0.13
    POSITIVE LOGITS
     face
    0.31
     hope
    0.29
     suppose
    0.27
     just
    0.26
     not
    0.25
     all
    0.22
     faces
    0.21
    face
    0.20
     us
    0.20
     Encrypt
    0.20
    Act Density 0.033%

    No Known Activations