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

    Neuronpedia

    INDEX
    Explanations

    phrases related to escape and evasion

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "escape" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inki
    -0.75
    reads
    -0.71
    ificent
    -0.69
    wow
    -0.61
     swear
    -0.58
     spare
    -0.58
    ¾
    -0.58
    spir
    -0.58
    iop
    -0.57
     stead
    -0.57
    POSITIVE LOGITS
     detection
    1.04
     unsc
    1.00
     confinement
    0.95
     captivity
    0.91
     capture
    0.84
     apprehension
    0.82
     punishment
    0.80
     Torment
    0.77
     justice
    0.77
     prosecution
    0.77
    Act Density 0.042%

    No Known Activations