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

    Neuronpedia

    INDEX
    Explanations

    references to the act of escaping or avoiding capture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wpdb
    -0.85
     Keith
    -0.76
    rizona
    -0.76
     Ton
    -0.72
    Keith
    -0.71
     Marston
    -0.69
    Ton
    -0.66
    NameValuePair
    -0.66
    ERMIN
    -0.65
     TON
    -0.65
    POSITIVE LOGITS
     Escape
    1.80
     escape
    1.80
     ESCAPE
    1.71
     escapes
    1.67
    Escape
    1.60
     escaped
    1.53
    ESCAPE
    1.45
    escape
    1.44
     escaping
    1.40
     esca
    1.31
    Act Density 0.073%

    No Known Activations