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

    Neuronpedia

    INDEX
    Explanations

    words related to legal or government actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases containing a specific repeated character or symbol

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ropes
    -0.76
     tyres
    -0.75
     condem
    -0.75
     vulner
    -0.74
     scissors
    -0.73
     apes
    -0.72
     tides
    -0.70
     grips
    -0.70
     clitor
    -0.68
     virginity
    -0.67
    POSITIVE LOGITS
    ï¸ı
    1.29
    âĶĢâĶĢ
    1.14
    conom
    0.95
    STER
    0.85
    °
    0.83
    uthor
    0.83
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    0.82
    cffffcc
    0.80
    ACP
    0.78
    \-
    0.77
    Act Density 0.143%

    No Known Activations