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

    Neuronpedia

    INDEX
    Explanations

    negations or expressions of dissent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )const
    -0.18
    üf
    -0.15
    Ĺı
    -0.15
    çĭ
    -0.14
    æł¹
    -0.14
    istrat
    -0.14
    acho
    -0.14
    errmsg
    -0.14
    yte
    -0.14
    chop
    -0.14
    POSITIVE LOGITS
    given
    0.15
     given
    0.15
     compact
    0.15
     Pacific
    0.15
     now
    0.15
     already
    0.14
    resse
    0.14
    257
    0.14
    uner
    0.13
    them
    0.13
    Act Density 0.000%

    No Known Activations