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

    Neuronpedia

    INDEX
    Explanations

    terms related to behavioral aspects or impacts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to behavioral science

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eous
    -0.93
    enthal
    -0.78
    smanship
    -0.76
    shall
    -0.76
    urat
    -0.74
     Maiden
    -0.71
    ources
    -0.70
    zona
    -0.69
    eem
    -0.69
    worthy
    -0.69
    POSITIVE LOGITS
    avior
    1.18
     behavioral
    0.97
     behavi
    0.90
    aviour
    0.89
     Behavioral
    0.85
     reperto
    0.85
     modification
    0.82
     behaviors
    0.81
    istics
    0.81
     sciences
    0.81
    Act Density 0.021%

    No Known Activations