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

    Neuronpedia

    INDEX
    Explanations

    opinions and subjective statements

    oai_token-act-pair · gpt-3.5-turbo

    expressions of opinion and subjective assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     prest
    -0.76
     Destroy
    -0.75
     END
    -0.74
     confiscated
    -0.73
     NOW
    -0.70
     explode
    -0.69
     Unle
    -0.66
     destroyed
    -0.66
     parachute
    -0.65
     fuse
    -0.64
    POSITIVE LOGITS
    âĢ
    1.21
    Personally
    1.11
    Regarding
    1.07
    particularly
    1.06
    Certainly
    1.03
    especially
    1.03
    Firstly
    1.03
     âĢ
    0.96
    Especially
    0.96
    However
    0.95
    Act Density 0.792%

    No Known Activations