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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the absence or presence of specific traits or behaviors

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a lack of progress or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oldown
    -0.75
    alez
    -0.72
    osate
    -0.70
    alt
    -0.68
    ksh
    -0.67
    levard
    -0.67
     Manufact
    -0.65
    =-=-=-=-
    -0.64
    apter
    -0.64
    ades
    -0.63
    POSITIVE LOGITS
     willingness
    1.20
     remorse
    1.02
     signs
    1.02
     resemblance
    1.01
     maturity
    1.00
     displeasure
    0.99
     penchant
    0.99
     propensity
    0.98
     resilience
    0.98
     gratitude
    0.96
    Act Density 0.155%

    No Known Activations