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

    Neuronpedia

    INDEX
    Explanations

    words related to ranks, positions, or levels

    oai_token-act-pair · gpt-3.5-turbo

    various forms of the word "final" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.80
    berman
    -0.76
    è¦ļéĨĴ
    -0.74
    PLIED
    -0.73
    schild
    -0.72
    ullivan
    -0.72
    awaru
    -0.72
    fortune
    -0.71
    Beg
    -0.69
    EEK
    -0.67
    POSITIVE LOGITS
    ysis
    1.33
    inal
    1.11
    ity
    1.05
    ient
    0.92
    pha
    0.90
    idad
    0.89
    phrine
    0.85
    culus
    0.84
    ITY
    0.82
    tarian
    0.82
    Act Density 0.016%

    No Known Activations