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

    Neuronpedia

    INDEX
    Explanations

    adjectives or adverbs used to describe something positively

    oai_token-act-pair · gpt-3.5-turbo

    words expressing exceptional qualities or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zie
    -0.81
    ppo
    -0.79
    hr
    -0.77
    enhagen
    -0.76
    pai
    -0.73
    cliffe
    -0.73
    ja
    -0.71
    ©¶æ
    -0.69
    worn
    -0.69
    embed
    -0.69
    POSITIVE LOGITS
     feats
    1.04
     rendition
    1.02
     feat
    0.99
     accomplishment
    0.93
     coincidence
    0.93
     likeness
    0.82
     amounts
    0.82
     achievement
    0.82
     lengths
    0.81
     accomplishments
    0.78
    Act Density 0.071%

    No Known Activations