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

    Neuronpedia

    INDEX
    Explanations

    news sources and reporting verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adj
    -0.15
    cene
    -0.15
     skim
    -0.14
    rapped
    -0.14
     ado
    -0.14
     impressed
    -0.14
    arse
    -0.14
    assin
    -0.13
     ppt
    -0.13
    itched
    -0.13
    POSITIVE LOGITS
     reporting
    0.27
     quoting
    0.27
     reported
    0.25
     quotes
    0.25
     quoted
    0.24
     quote
    0.24
    reported
    0.24
     exclusive
    0.24
     exclusively
    0.23
    quotes
    0.23
    Act Density 0.051%

    No Known Activations