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

    Neuronpedia

    INDEX
    Explanations

    adjectives expressing strong emotional reactions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong emotional reactions or judgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ailability
    -0.74
    roma
    -0.72
     downed
    -0.72
    rongh
    -0.71
    arta
    -0.68
    haar
    -0.68
    ournal
    -0.66
    igate
    -0.66
    obo
    -0.66
     carrier
    -0.64
    POSITIVE LOGITS
     Dragonbound
    0.83
     Carlson
    0.77
     enough
    0.76
     Osw
    0.70
    imaru
    0.70
     Pwr
    0.70
     Beir
    0.69
     irony
    0.66
    Leaks
    0.65
     coincidence
    0.64
    Act Density 0.182%

    No Known Activations