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

    Neuronpedia

    INDEX
    Explanations

    words related to vivid emotions or actions

    oai_token-act-pair · gpt-3.5-turbo

    actions and activities that convey a sense of enthusiasm or excitement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     shedding
    -0.73
     attribution
    -0.71
     informing
    -0.68
     countering
    -0.67
     serving
    -0.66
     unlocking
    -0.65
     shaming
    -0.64
     withholding
    -0.63
     reiter
    -0.63
     clar
    -0.63
    POSITIVE LOGITS
    igrated
    1.56
    wrote
    1.45
    ivated
    1.44
    elled
    1.42
    ailed
    1.38
    ked
    1.38
    anced
    1.37
    aned
    1.37
    ored
    1.37
    iated
    1.36
    Act Density 0.332%

    No Known Activations