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

    Neuronpedia

    INDEX
    Explanations

    high-frequency common words and references in technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isty
    -0.16
    olic
    -0.15
    abe
    -0.15
    mania
    -0.15
    esen
    -0.14
    erged
    -0.14
     Bills
    -0.14
    ekler
    -0.14
    kre
    -0.14
     neger
    -0.14
    POSITIVE LOGITS
    CSI
    0.15
    ounce
    0.15
     burner
    0.14
    isoft
    0.14
    hol
    0.14
    aper
    0.14
     Yoshi
    0.14
    awah
    0.14
    prise
    0.14
     bite
    0.14
    Act Density 0.003%

    No Known Activations