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

    Neuronpedia

    INDEX
    Explanations

    expressions related to speaking or communicating

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Aiheesta
    -0.61
     />";
    -0.59
     immédi
    -0.56
     saan
    -0.56
     Mainland
    -0.55
     <<<<<<<<<<<<<<
    -0.55
    DebuggerNonUser
    -0.54
     tambin
    -0.54
    évaluateur
    -0.54
    商品説明
    -0.52
    POSITIVE LOGITS
     goodbye
    1.30
     hello
    1.01
     yes
    0.83
     farewell
    0.81
    goodbye
    0.77
     thank
    0.74
     nothing
    0.73
    er
    0.72
     prayers
    0.69
     aloud
    0.67
    Act Density 0.100%

    No Known Activations