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

    Neuronpedia

    INDEX
    Explanations

    structured data or code segments with a specific syntax or format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.93
     Monfieur
    -0.76
     raiſ
    -0.73
     myſelf
    -0.72
    RegressionTest
    -0.71
     ſeveral
    -0.71
     Jefus
    -0.71
     himſelf
    -0.71
    "]();
    -0.69
     Efq
    -0.69
    POSITIVE LOGITS
     =
    0.71
    =
    0.65
     $=\
    0.61
     $=
    0.61
     }=\
    0.61
    Portail
    0.59
    Læs
    0.59
    >=</
    0.58
     $=$
    0.58
    _=
    0.57
    Act Density 0.307%

    No Known Activations