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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and time-related information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    λα
    -0.16
    steen
    -0.15
    achers
    -0.14
    atcher
    -0.14
     Nam
    -0.14
    iger
    -0.14
     Samuel
    -0.14
    ikit
    -0.14
    Serialization
    -0.13
     Cass
    -0.13
    POSITIVE LOGITS
    adow
    0.15
    gua
    0.15
    (gcf
    0.15
     Mort
    0.15
     ног
    0.14
     ÙĦÛĮÚ¯
    0.14
    asta
    0.14
    uzey
    0.14
    ource
    0.14
    .Invariant
    0.14
    Act Density 0.001%

    No Known Activations