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

    Neuronpedia

    INDEX
    Explanations

    names of individuals and companies

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of individuals and companies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unspecified
    -0.72
    erness
    -0.64
     circumstance
    -0.61
    ãĤ¢ãĥ«
    -0.60
     therap
    -0.58
     ident
    -0.58
     foul
    -0.58
    eatures
    -0.57
     coinc
    -0.55
     offence
    -0.54
    POSITIVE LOGITS
     etc
    0.83
     or
    0.77
    dan
    0.72
    uggest
    0.70
    existent
    0.69
    ouch
    0.68
    rimp
    0.68
    ADRA
    0.66
    olt
    0.65
    bler
    0.63
    Act Density 0.369%

    No Known Activations