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

    Neuronpedia

    INDEX
    Explanations

    references to resources, particularly related to reserves and contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erve
    -0.33
    bourne
    -0.28
    idential
    -0.28
    tober
    -0.27
    inez
    -0.26
    idente
    -0.26
    osoph
    -0.26
    andez
    -0.25
    emporary
    -0.25
    ERVED
    -0.25
    POSITIVE LOGITS
    ry
    0.21
    ention
    0.19
    reo
    0.17
    imiter
    0.17
    dum
    0.16
    keley
    0.16
    igli
    0.16
    ror
    0.15
    tero
    0.15
    ockey
    0.15
    Act Density 0.040%

    No Known Activations