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

    Neuronpedia

    INDEX
    Explanations

    words related to physical movements involving force

    oai_token-act-pair · gpt-3.5-turbo

    words related to jumping or leaping actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cogn
    -0.78
     contem
    -0.64
     ADA
    -0.61
     Serv
    -0.58
     Lear
    -0.58
     dishes
    -0.58
     disabilities
    -0.58
     vari
    -0.58
     badges
    -0.58
     dish
    -0.57
    POSITIVE LOGITS
    umping
    4.02
    umped
    2.77
    UMP
    1.59
    ump
    1.45
    umper
    1.40
    ounding
    1.17
    umpy
    1.09
    umps
    1.08
     pumping
    1.08
    itching
    1.03
    Act Density 0.020%

    No Known Activations