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

    Neuronpedia

    INDEX
    Explanations

    instances of numerical values or symbols

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     reflex
    -0.78
     mounts
    -0.71
     clitor
    -0.70
     Mirage
    -0.70
     pigeon
    -0.68
     synerg
    -0.67
     apes
    -0.67
     vulner
    -0.67
     lapse
    -0.66
     pleasures
    -0.66
    POSITIVE LOGITS
    ï¸ı
    1.44
    âĶĢâĶĢ
    1.01
    ternity
    0.99
    ACP
    0.92
    uthor
    0.90
    $
    0.90
    cffffcc
    0.89
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    0.88
    audi
    0.88
    \-
    0.86
    Act Density 1.415%

    No Known Activations