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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditional or contextual actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ERY
    -0.16
     Bowen
    -0.15
    zte
    -0.15
    URA
    -0.15
    onian
    -0.14
    彡
    -0.14
    erty
    -0.14
    uer
    -0.14
     Ske
    -0.14
    usan
    -0.14
    POSITIVE LOGITS
    Å©
    0.15
    å²³
    0.15
    òa
    0.15
     Král
    0.14
    ube
    0.14
    phinx
    0.14
    ÑĥÑĢ
    0.14
    atham
    0.14
    jax
    0.14
    .Encoding
    0.14
    Act Density 0.001%

    No Known Activations