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

    Neuronpedia

    INDEX
    Explanations

    future-oriented statements related to actions or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cke
    -0.20
    ersen
    -0.19
    ta
    -0.15
    ýt
    -0.15
     Ung
    -0.14
     kings
    -0.14
    itional
    -0.14
    ollow
    -0.14
    mn
    -0.14
     Bos
    -0.14
    POSITIVE LOGITS
    Ïģκ
    0.15
    TRS
    0.15
    PTS
    0.15
    祥
    0.14
    .instant
    0.14
    ologne
    0.14
     Perm
    0.14
    ädchen
    0.14
    RIPT
    0.14
    uest
    0.14
    Act Density 0.157%

    No Known Activations