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

    Neuronpedia

    INDEX
    Explanations

    keywords related to searching or locating something

    oai_token-act-pair · gpt-3.5-turbo

    the word "find" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     paced
    -0.72
     concess
    -0.71
     partic
    -0.68
     Buff
    -0.64
    perty
    -0.63
    assisted
    -0.61
    inion
    -0.60
    puff
    -0.60
    slow
    -0.60
    psey
    -0.60
    POSITIVE LOGITS
    使
    0.86
    Ô
    0.86
    ById
    0.82
    ãĤ¼
    0.80
    ibility
    0.77
    omething
    0.76
    ource
    0.76
    -+-+
    0.76
    upon
    0.75
    ãĤ¦
    0.74
    Act Density 0.068%

    No Known Activations