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

    Neuronpedia

    INDEX
    Explanations

    references to programming functions or methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    taboola
    -0.71
    gie
    -0.69
     obser
    -0.63
    sbm
    -0.62
     roy
    -0.60
    ãĤ¼ãĤ¦ãĤ¹
    -0.59
     defic
    -0.59
     detrim
    -0.59
     Shame
    -0.59
     behavi
    -0.58
    POSITIVE LOGITS
    odcast
    1.23
    ulse
    1.20
    olicy
    1.19
    ivot
    1.18
    ixels
    1.15
    olitics
    1.13
    resents
    1.12
    ixel
    1.10
    inion
    1.10
    ression
    1.09
    Act Density 0.376%

    No Known Activations