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

    Neuronpedia

    INDEX
    Explanations

    claims related to research and studies, particularly focusing on effects, evidence, and conclusions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     acron
    -0.67
     Obj
    -0.65
     Unic
    -0.65
     Specifications
    -0.64
     Pon
    -0.64
     Ital
    -0.63
     Kut
    -0.63
    RAFT
    -0.63
     Ded
    -0.63
     Peb
    -0.63
    POSITIVE LOGITS
     beneficial
    1.18
     impair
    1.15
     inhibit
    1.10
     stimulate
    1.09
     calming
    1.08
     stimulating
    1.05
     affect
    1.04
    acea
    1.04
     induce
    1.03
    Effects
    1.03
    Act Density 0.882%

    No Known Activations