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

    Neuronpedia

    INDEX
    Explanations

    words related to famous individuals

    oai_token-act-pair · gpt-3.5-turbo

    words associated with deception or lack of integrity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     craving
    -0.70
     Ramadan
    -0.70
     reliance
    -0.68
     lapse
    -0.68
     neoc
    -0.68
    inished
    -0.68
     famine
    -0.65
     behold
    -0.65
    abase
    -0.65
     embargo
    -0.62
    POSITIVE LOGITS
    cheon
    0.84
    hett
    0.82
    itzer
    0.75
    arios
    0.72
    berus
    0.69
    lator
    0.68
    iron
    0.68
    uli
    0.68
    udo
    0.67
    river
    0.66
    Act Density 0.070%

    No Known Activations