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

    Neuronpedia

    INDEX
    Explanations

    bullet points or list entries in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    innig
    -0.83
     --}}
    -0.83
    zwe
    -0.81
    ksjon
    -0.79
     Jacob
    -0.77
    qos
    -0.76
     Garg
    -0.76
     Luch
    -0.75
     Zamb
    -0.71
    ambig
    -0.71
    POSITIVE LOGITS
    .•
    1.52
    ••
    1.47
     •
    1.35
    •••
    1.33
    °•
    1.29
    ••••
    1.27
    er
    1.20
    )•
    1.16
    ~•
    1.13
     ••
    1.07
    Act Density 0.039%

    No Known Activations