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

    Neuronpedia

    INDEX
    Explanations

    repeated usages of the word "We"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lights
    -0.17
    unda
    -0.15
    oub
    -0.15
    fu
    -0.15
    rim
    -0.15
    bÃŃ
    -0.15
    arra
    -0.15
    ctor
    -0.15
    dez
    -0.15
    double
    -0.15
    POSITIVE LOGITS
    avers
    0.25
    imar
    0.24
    bsp
    0.23
    athers
    0.23
    itere
    0.22
    ave
    0.21
    asley
    0.21
    brtc
    0.21
    aving
    0.21
    aver
    0.21
    Act Density 0.031%

    No Known Activations