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

    Neuronpedia

    INDEX
    Explanations

    information about specific topics or entities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "find out more about."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sabha
    -0.86
    ©¶æ¥µ
    -0.80
    OGR
    -0.75
     teasp
    -0.73
    mouth
    -0.72
    rang
    -0.68
    amiya
    -0.67
    roma
    -0.65
    ा
    -0.65
    Creat
    -0.64
    POSITIVE LOGITS
     how
    0.90
     whats
    0.84
     why
    0.75
     specifics
    0.74
     details
    0.70
     topics
    0.69
     Yourself
    0.67
    annel
    0.63
     yourself
    0.63
     facets
    0.63
    Act Density 0.053%

    No Known Activations