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

    Neuronpedia

    INDEX
    Explanations

    words related to avoiding or escaping situations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to avoiding or evading challenges or obstacles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onial
    -0.81
    umption
    -0.73
     antioxid
    -0.66
    ivil
    -0.65
    Premium
    -0.64
    apsed
    -0.63
    ension
    -0.63
    aster
    -0.63
    oyal
    -0.62
    inki
    -0.61
    POSITIVE LOGITS
     dodge
    0.81
    tails
    0.81
    FACE
    0.74
     dodging
    0.74
    acle
    0.73
     evasion
    0.73
    balls
    0.73
     detection
    0.72
    poke
    0.72
    asive
    0.72
    Act Density 0.044%

    No Known Activations