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

    Neuronpedia

    INDEX
    Explanations

    phrases related to launching or beginning a project or campaign

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "para" and related expressions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    士
    -0.92
    Ö¼
    -0.84
    esley
    -0.77
    ories
    -0.74
    Reviewer
    -0.74
    bread
    -0.74
    ORE
    -0.72
    robe
    -0.71
    æ©
    -0.71
    sburg
    -0.70
    POSITIVE LOGITS
     para
    1.14
     compr
    1.09
     psychiat
    0.86
     mosqu
    0.85
     millenn
    0.83
     challeng
    0.79
    esthes
    0.76
     pse
    0.76
     cling
    0.75
    ilitary
    0.74
    Act Density 0.006%

    No Known Activations