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

    Neuronpedia

    INDEX
    Explanations

    references or mentions of websites or URLs containing specific keywords or phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to specific internet domains or content related to media and film

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     opp
    -0.81
     HIP
    -0.81
     Hen
    -0.80
     Opp
    -0.80
     Amen
    -0.80
     heter
    -0.79
     Hirosh
    -0.78
     Hour
    -0.78
     Gall
    -0.78
     Piper
    -0.77
    POSITIVE LOGITS
    ve
    1.44
    ves
    1.27
    vel
    1.21
    vere
    1.20
    vell
    1.20
    ved
    1.17
    vable
    1.15
    ver
    1.08
    ving
    1.06
    VE
    1.02
    Act Density 0.308%

    No Known Activations