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

    Neuronpedia

    INDEX
    Explanations

    mentions of a person named "Collins."

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    lisher
    -0.93
    à¨
    -0.89
    GD
    -0.84
    765
    -0.83
    fare
    -0.83
    dig
    -0.83
    ETA
    -0.83
    ICAN
    -0.83
    udeb
    -0.83
    ODUCT
    -0.81
    POSITIVE LOGITS
    ively
    1.48
    ues
    1.15
    ograms
    1.11
    daq
    1.11
    uries
    1.10
    cape
    1.08
    esis
    1.06
    es
    1.04
    worth
    1.02
    uing
    1.02
    Act Density 1.303%

    No Known Activations