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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "sign" and its variations, indicating agreements or contracts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iyel
    -0.16
    θμ
    -0.15
    uz
    -0.15
    usz
    -0.14
    ozor
    -0.14
    acr
    -0.14
    issen
    -0.14
    egr
    -0.14
    _MUX
    -0.14
    689
    -0.13
    POSITIVE LOGITS
    ificantly
    0.23
    atories
    0.19
    alled
    0.18
    atures
    0.18
    ificance
    0.18
    ificant
    0.16
    aldi
    0.16
     çŃ
    0.16
    _allocate
    0.16
    /sign
    0.16
    Act Density 0.027%

    No Known Activations