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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expressing impossibility or strong denial

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating impossibility or certainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheus
    -0.87
    anmar
    -0.85
    uster
    -0.79
    aples
    -0.74
    cius
    -0.74
     livest
    -0.73
    itton
    -0.72
    iery
    -0.72
     dormant
    -0.71
    itures
    -0.71
    POSITIVE LOGITS
     whatsoever
    0.96
    point
    0.86
    fare
    0.83
    PASS
    0.76
     WAY
    0.73
    Fuck
    0.72
    YY
    0.72
    Way
    0.70
    way
    0.68
    bos
    0.68
    Act Density 0.016%

    No Known Activations