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

    Neuronpedia

    INDEX
    Explanations

    relevant information or content

    oai_token-act-pair · gpt-3.5-turbo

    expressions of relevancy or significance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rette
    -0.94
    cker
    -0.73
    anus
    -0.73
    boat
    -0.71
    uber
    -0.71
    rug
    -0.70
    jah
    -0.68
    rix
    -0.68
    hesda
    -0.67
    usk
    -0.67
    POSITIVE LOGITS
     contextual
    0.81
     è£ıè
    0.80
     newsp
    0.80
     predic
    0.74
     explan
    0.74
    relevant
    0.73
    é¾įå¥ij士
    0.73
    ively
    0.72
     material
    0.72
    ="#
    0.72
    Act Density 0.018%

    No Known Activations