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

    Neuronpedia

    INDEX
    Explanations

    names or titles preceded by "Mr."

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals and their associated roles or actions in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ModLoader
    -0.66
    etheless
    -0.65
     chem
    -0.65
     womb
    -0.61
     AAC
    -0.57
     date
    -0.57
    ĪĴ
    -0.57
    dylib
    -0.56
     Entered
    -0.56
    ãĥ¼ãĥĨãĤ£
    -0.56
    POSITIVE LOGITS
    arde
    0.84
    oute
    0.81
    ij士
    0.80
    izo
    0.80
    zinski
    0.78
    ray
    0.75
     apologised
    0.74
    idy
    0.72
    igl
    0.71
    Äĩ
    0.70
    Act Density 0.087%

    No Known Activations