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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to belief and magic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orne
    -0.15
    uguay
    -0.15
    .ribbon
    -0.15
    éĥİ
    -0.15
    remen
    -0.14
    thinkable
    -0.14
    ergy
    -0.14
     CONTRIBUTORS
    -0.14
    RIES
    -0.14
    unate
    -0.13
    POSITIVE LOGITS
    omba
    0.16
    yp
    0.16
     Crit
    0.15
     Crack
    0.15
    696
    0.14
     Bilim
    0.14
    etti
    0.14
    321
    0.14
    atest
    0.14
     ac
    0.13
    Act Density 0.213%

    No Known Activations