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

    Neuronpedia

    INDEX
    Explanations

    names that contain the word "Mac" along with a number that follows

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Mac" across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     NETWORK
    -0.76
    ãĥ¼ãĥĨ
    -0.74
    ãĥĦ
    -0.71
     Tend
    -0.68
    ICLE
    -0.66
    æĢ
    -0.66
     sidx
    -0.65
    ãĥ¼ãĥĨãĤ£
    -0.64
    ा
    -0.63
    Reloaded
    -0.63
    POSITIVE LOGITS
    intosh
    1.29
    abre
    1.07
    pher
    1.03
    donald
    1.03
    Leod
    0.96
    rosc
    0.94
    rob
    0.94
    lean
    0.88
    ross
    0.87
    ro
    0.87
    Act Density 0.008%

    No Known Activations