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

    Neuronpedia

    INDEX
    Explanations

    instances of people being pleased with different situations or events

    oai_token-act-pair · gpt-3.5-turbo

    instances of satisfaction or approval

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opic
    -0.88
    amen
    -0.74
    çīĪ
    -0.72
    ngth
    -0.69
     stove
    -0.69
    opers
    -0.66
    ocular
    -0.65
    ammy
    -0.65
    arin
    -0.64
    ut
    -0.64
    POSITIVE LOGITS
    ienced
    0.77
    iated
    0.72
    joy
    0.71
     Shad
    0.71
    vale
    0.67
    ragon
    0.67
    liness
    0.67
    issance
    0.66
     onlook
    0.65
    jad
    0.65
    Act Density 0.041%

    No Known Activations