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

    Neuronpedia

    INDEX
    Explanations

    references related to scientific studies, publications, and research findings

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    nesday
    -0.91
    wards
    -0.84
     Frozen
    -0.83
    å¹
    -0.83
    assador
    -0.83
    romeda
    -0.81
    adobe
    -0.80
    theless
    -0.78
    etheless
    -0.78
    uador
    -0.78
    POSITIVE LOGITS
    ullivan
    0.93
    heny
    0.82
    ONSORED
    0.82
     explanatory
    0.80
     bip
    0.80
    itzer
    0.80
    ozo
    0.79
    agall
    0.79
    OHN
    0.77
     psy
    0.77
    Act Density 0.803%

    No Known Activations