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

    Neuronpedia

    INDEX
    Explanations

    words related to physical actions involving hands or hand-related activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to pointing or gesturing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Richards
    -0.80
     QC
    -0.79
    iatus
    -0.73
    ulhu
    -0.69
     âĶľ
    -0.66
     Diary
    -0.65
    HCR
    -0.65
     Discipline
    -0.65
     Atmosp
    -0.63
     EntityItem
    -0.63
    POSITIVE LOGITS
    based
    1.16
    operated
    1.14
    sized
    1.12
    backed
    1.08
    forward
    1.08
    to
    1.04
    shaped
    1.04
    themed
    1.03
    eyed
    1.02
    eye
    1.01
    Act Density 0.136%

    No Known Activations