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

    Neuronpedia

    INDEX
    Explanations

    words related to physical gestures or actions involving hands

    oai_token-act-pair · gpt-3.5-turbo

    phrases or themes related to criticism or negative experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Richards
    -0.81
    iatus
    -0.74
    ãģ®éŃĶ
    -0.71
    HCR
    -0.69
     QC
    -0.68
    ulhu
    -0.66
     Burnett
    -0.65
     âĶľ
    -0.64
     Cox
    -0.63
     Nich
    -0.63
    POSITIVE LOGITS
    eye
    1.11
    based
    1.08
    sized
    1.08
    headed
    1.04
    related
    1.02
    themed
    1.02
    pain
    1.01
    shaped
    0.99
    operated
    0.98
    tw
    0.98
    Act Density 0.097%

    No Known Activations