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

    Neuronpedia

    INDEX
    Explanations

    names of people or characters

    oai_token-act-pair · gpt-3.5-turbo

    names and references to specific individuals or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    loo
    -0.83
    orthy
    -0.81
    nikov
    -0.80
    atile
    -0.78
    leader
    -0.76
    brance
    -0.76
    ndra
    -0.75
    ophers
    -0.74
    opers
    -0.74
    arity
    -0.74
    POSITIVE LOGITS
    rawl
    0.77
     print
    0.77
     Print
    0.76
     Fey
    0.73
     Suns
    0.70
    astical
    0.69
     Mia
    0.69
    Downloadha
    0.68
    ointed
    0.67
     Dia
    0.67
    Act Density 0.028%

    No Known Activations