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

    Neuronpedia

    INDEX
    Explanations

    action-related words and terms related to sports

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    )."
    -0.73
    )).
    -0.71
    ĪĴ
    -0.70
    ]."
    -0.68
     behav
    -0.67
    ©¶æ
    -0.67
    ]).
    -0.67
    odan
    -0.66
    ĨĴ
    -0.65
    )"
    -0.65
    POSITIVE LOGITS
     thanks
    0.89
    !
    0.86
     lately
    0.83
     nowadays
    0.78
    —
    0.75
    .
    0.74
     –
    0.70
    ;
    0.70
     —
    0.69
     but
    0.69
    Act Density 0.557%

    No Known Activations