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

    Neuronpedia

    INDEX
    Explanations

    references to evacuation and crisis management situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÙĨØ´
    -0.16
    ¯u
    -0.15
    اÙĦس
    -0.14
    ÑĢоÑģÑĤ
    -0.14
    ashi
    -0.14
    ernote
    -0.13
    ccd
    -0.13
    _frequency
    -0.13
    ctl
    -0.13
    _nth
    -0.13
    POSITIVE LOGITS
     evac
    0.39
     evacuation
    0.39
     evacuate
    0.36
     evacuated
    0.32
     escape
    0.28
     Escape
    0.25
     exit
    0.24
    Escape
    0.23
     escaping
    0.23
     escapes
    0.23
    Act Density 0.107%

    No Known Activations