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

    Neuronpedia

    INDEX
    Explanations

    terms related to actual outcomes versus expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ppins
    -0.78
     entgegen
    -0.77
    engi
    -0.72
     Ferri
    -0.69
     Arquivado
    -0.69
    Bridget
    -0.68
     conquistar
    -0.67
    rmtree
    -0.67
    ebra
    -0.67
    Multiline
    -0.66
    POSITIVE LOGITS
    ACTUAL
    1.02
     Actual
    1.02
    Usual
    1.00
    Actual
    1.00
     actual
    0.99
     Usual
    0.97
    usual
    0.95
     ACTUAL
    0.92
     usual
    0.89
    actual
    0.85
    Act Density 0.082%

    No Known Activations