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

    Neuronpedia

    INDEX
    Explanations

    terms related to enabling and disabling functions or features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ancellable
    -0.08
    elves
    -0.08
    rei
    -0.07
    жд
    -0.07
    oring
    -0.07
    ishly
    -0.07
    inee
    -0.07
    ÅĻád
    -0.07
    خاÙĨÙĩ
    -0.07
    íĦ¸
    -0.07
    POSITIVE LOGITS
    /disable
    0.20
    ment
    0.16
    /dis
    0.12
    ments
    0.10
    -bodied
    0.09
    VertexAttribArray
    0.08
    /en
    0.07
    -disable
    0.07
    405
    0.07
    more
    0.07
    Act Density 0.043%

    No Known Activations