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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the introduction of a concept or proposal

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to the concept of "idea."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ago
    -0.77
     Peaks
    -0.66
    çĦ
    -0.65
    Oper
    -0.65
    opard
    -0.63
    eworthy
    -0.62
    lake
    -0.61
    ndum
    -0.61
     ILCS
    -0.60
    hma
    -0.59
    POSITIVE LOGITS
    ually
    1.02
     idea
    0.83
    atical
    0.82
     moot
    0.79
    reprene
    0.76
    escape
    0.71
    orial
    0.71
     hatched
    0.71
    eers
    0.70
    ual
    0.69
    Act Density 0.036%

    No Known Activations