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

    Neuronpedia

    INDEX
    Explanations

    instances where something or someone is physically trapped or unable to move

    oai_token-act-pair · gpt-3.5-turbo

    instances of being "stuck" or "trapped" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     derived
    -0.68
     confir
    -0.61
    vernment
    -0.60
    iances
    -0.59
    1016
    -0.58
     Transparency
    -0.58
    urai
    -0.58
     dispel
    -0.58
    qua
    -0.58
    onse
    -0.58
    POSITIVE LOGITS
     between
    0.89
     somewhere
    0.88
     inside
    0.86
    locked
    0.86
     waiting
    0.86
     staring
    0.83
    between
    0.80
    ousel
    0.80
     upside
    0.79
     wondering
    0.78
    Act Density 0.061%

    No Known Activations