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

    Neuronpedia

    INDEX
    Explanations

    references to novels and literary works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fully
    -0.21
    aan
    -0.16
    ed
    -0.15
    allest
    -0.15
    fulness
    -0.14
    295
    -0.14
    fre
    -0.14
    ÙĪØ·
    -0.14
    fit
    -0.14
    wards
    -0.14
    POSITIVE LOGITS
    -length
    0.30
    ization
    0.29
    ized
    0.27
    izations
    0.27
    istic
    0.27
    lette
    0.26
    ists
    0.26
    isation
    0.25
    ised
    0.25
    ty
    0.22
    Act Density 0.014%

    No Known Activations