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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating frequency or prevalence within a specific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sy
    -0.15
     mog
    -0.15
    Via
    -0.14
     neger
    -0.14
    ()(
    -0.14
    CCC
    -0.14
    lexical
    -0.13
     original
    -0.13
    lashes
    -0.13
     Via
    -0.13
    POSITIVE LOGITS
    rome
    0.19
    heid
    0.16
    stown
    0.15
    umph
    0.15
    ãĥĥãĥĹ
    0.14
    ifold
    0.14
    ίο
    0.14
    dej
    0.14
    adden
    0.14
    .glide
    0.14
    Act Density 0.135%

    No Known Activations