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

    Neuronpedia

    INDEX
    Explanations

    the word "find" followed by an object or a situation

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal opinions or evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idium
    -0.73
     concess
    -0.72
    perty
    -0.64
     bailed
    -0.63
     dome
    -0.60
    istry
    -0.59
     slash
    -0.58
    ivari
    -0.57
    draft
    -0.56
    isphere
    -0.56
    POSITIVE LOGITS
     myself
    0.80
     irresistible
    0.77
    ¶æ
    0.74
     inspiration
    0.73
     fault
    0.72
     satisfaction
    0.72
     attractive
    0.71
    ById
    0.71
     objectionable
    0.70
    ļé
    0.70
    Act Density 0.059%

    No Known Activations