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

    Neuronpedia

    INDEX
    Explanations

    phrases related to reporting and errors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     onBind
    -0.58
     destinados
    -0.58
     destinada
    -0.58
    pust
    -0.55
    ष्य
    -0.54
    minecraftforge
    -0.53
    ANTAGES
    -0.53
    ménage
    -0.53
     darin
    -0.51
    rawQuery
    -0.51
    POSITIVE LOGITS
     reporting
    2.05
     reported
    1.99
     Reporting
    1.88
     REPORTING
    1.77
    Reporting
    1.76
     Reported
    1.76
    reported
    1.73
    reporting
    1.70
    Reported
    1.66
     reports
    1.65
    Act Density 0.164%

    No Known Activations