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

    Neuronpedia

    INDEX
    Explanations

    technical terms, such as software and organization names

    oai_token-act-pair · gpt-3.5-turbo

    references to computer hacking and institutions, especially related to education or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    staking
    -0.67
    Reviewer
    -0.66
    oaded
    -0.63
     tremend
    -0.61
    ancial
    -0.58
    awed
    -0.57
     strengths
    -0.56
    rather
    -0.56
    different
    -0.55
     sidew
    -0.55
    POSITIVE LOGITS
     âĵĺ
    1.05
     Extras
    0.73
     Miscellaneous
    0.70
     TBA
    0.69
     ----------------
    0.67
     (?,
    0.67
     Duo
    0.61
     Suite
    0.61
     Profile
    0.61
    ":["
    0.61
    Act Density 0.452%

    No Known Activations