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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing a conditional or collaborative nature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ways
    -0.16
    _DEFINED
    -0.15
    abbo
    -0.14
    wake
    -0.14
    idf
    -0.14
    lick
    -0.14
    essel
    -0.14
    .templates
    -0.14
    inet
    -0.14
    mentation
    -0.14
    POSITIVE LOGITS
     regard
    0.27
     regards
    0.24
     respect
    0.22
    standing
    0.20
    holds
    0.20
    stood
    0.20
    outh
    0.19
    oji
    0.18
    .Tween
    0.17
    ered
    0.16
    Act Density 0.349%

    No Known Activations