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

    Neuronpedia

    INDEX
    Explanations

    terms related to licensing and regulatory compliance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wards
    -0.18
    ERSHEY
    -0.16
    iness
    -0.16
    unci
    -0.16
    peÄį
    -0.15
    roller
    -0.15
     whistle
    -0.15
     Gerard
    -0.15
    shine
    -0.14
    ward
    -0.14
    POSITIVE LOGITS
    plate
    0.27
    _plate
    0.25
     plate
    0.24
     plates
    0.24
    es
    0.23
     Plate
    0.23
    Plate
    0.23
    /lic
    0.20
    ory
    0.20
     agreement
    0.19
    Act Density 0.019%

    No Known Activations