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

    Neuronpedia

    INDEX
    Explanations

    descriptive terms related to emotions and sensations

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong emotional states or reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Miss
    -0.68
     Tycoon
    -0.65
    zag
    -0.64
     Overview
    -0.63
    advant
    -0.63
    figure
    -0.62
     strugg
    -0.61
     Corruption
    -0.61
    write
    -0.61
    submit
    -0.60
    POSITIVE LOGITS
     palpable
    1.33
     misplaced
    1.21
     heightened
    1.13
     unfounded
    1.13
     contagious
    1.08
     understandable
    1.08
     mutual
    1.07
     stoked
    1.07
     tempered
    1.04
     warranted
    1.04
    Act Density 0.201%

    No Known Activations