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

    Neuronpedia

    INDEX
    Explanations

    phrases or words related to familiarity or being acquainted with something

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the word "familiar."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chance
    -0.85
    hap
    -0.78
    prus
    -0.73
    tan
    -0.72
    etheus
    -0.72
    aminer
    -0.71
    reme
    -0.70
    ©¶æ
    -0.70
    scoring
    -0.69
    psey
    -0.68
    POSITIVE LOGITS
    ization
    0.92
    ized
    0.91
    isable
    0.90
    izing
    0.89
    izations
    0.86
    isation
    0.84
     familiar
    0.83
    ity
    0.83
    ised
    0.82
    iliar
    0.81
    Act Density 0.015%

    No Known Activations