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

    Neuronpedia

    INDEX
    Explanations

    negative sentiment and criticism towards various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     caveats
    -0.80
     loopholes
    -0.70
     kindness
    -0.69
     snap
    -0.67
     decency
    -0.66
     swoop
    -0.66
     uncertainties
    -0.65
     Loll
    -0.64
     assumptions
    -0.63
     Panic
    -0.63
    POSITIVE LOGITS
    founder
    1.39
    director
    1.24
    leader
    1.19
    chair
    1.17
    authored
    1.16
    signed
    1.14
    creator
    1.11
    producing
    1.11
    author
    1.10
    founded
    1.08
    Act Density 0.012%

    No Known Activations