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

    Neuronpedia

    INDEX
    Explanations

    references to the name "Or" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ey
    -0.17
    irut
    -0.17
    ycastle
    -0.16
    моÑĢ
    -0.16
    éra
    -0.16
    elian
    -0.15
    artment
    -0.15
    gli
    -0.15
    gether
    -0.15
    еÑĤÑĥ
    -0.15
    POSITIVE LOGITS
    ourke
    0.26
    ignal
    0.23
    iginal
    0.22
    chest
    0.21
    naments
    0.19
    tega
    0.19
    chestra
    0.18
    zech
    0.18
    hea
    0.18
    IGNAL
    0.17
    Act Density 0.033%

    No Known Activations