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

    Neuronpedia

    INDEX
    Explanations

    names of individuals, likely related to media or public figures

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns or names of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¤ãĥĪ
    -0.83
    DAQ
    -0.79
    cffffcc
    -0.69
    ngth
    -0.61
    arine
    -0.60
     Erin
    -0.56
    ERG
    -0.56
    CVE
    -0.56
     til
    -0.56
    IUM
    -0.55
    POSITIVE LOGITS
    acco
    0.84
     Lines
    0.71
    appa
    0.66
    asca
    0.64
    batch
    0.63
    bia
    0.61
     Archdemon
    0.61
    aldi
    0.59
    antz
    0.58
    leck
    0.57
    Act Density 0.101%

    No Known Activations