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

    Neuronpedia

    INDEX
    Explanations

    large numerical quantities and statistics

    oai_token-act-pair · gpt-3.5-turbo

    quantitative data or numerical information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    essor
    -0.56
     ])
    -0.50
    ĪĴ
    -0.50
    å°Ĩ
    -0.49
    ãĥĻ
    -0.47
     risked
    -0.47
    ãģĹ
    -0.47
    vae
    -0.47
    ¬¼
    -0.46
    °
    -0.46
    POSITIVE LOGITS
     whereas
    0.82
    ;
    0.81
     because
    0.78
    .
    0.71
     insofar
    0.68
     since
    0.68
    .;
    0.68
     although
    0.67
     unless
    0.67
     thanks
    0.67
    Act Density 1.190%

    No Known Activations