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

    Neuronpedia

    INDEX
    Explanations

    phrases related to particular names, possibly "Per" or similar

    oai_token-act-pair · gpt-3.5-turbo

    the occurrences of the word "Per"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uminati
    -0.73
    LCS
    -0.73
    gha
    -0.71
    GGGGGGGG
    -0.68
    swick
    -0.67
    ties
    -0.65
    roo
    -0.65
    jing
    -0.65
    aze
    -0.62
    hello
    -0.62
    POSITIVE LOGITS
     Per
    3.63
    Per
    2.56
     PER
    1.87
    per
    1.78
     per
    1.53
    PER
    1.32
     Peru
    1.24
    perm
    1.22
     Pen
    1.19
     perm
    1.13
    Act Density 0.004%

    No Known Activations