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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the origin or source of something

    oai_token-act-pair · gpt-3.5-turbo

    the word "from" and its variations, indicating origins or sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idav
    -0.81
    fps
    -0.71
    queue
    -0.69
    perty
    -0.69
    ftime
    -0.67
    iar
    -0.67
    nex
    -0.67
    mouth
    -0.66
    itional
    -0.66
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.65
    POSITIVE LOGITS
     somewhere
    1.25
     nowhere
    1.22
     afar
    1.21
     abroad
    1.19
     elsewhere
    1.06
     scratch
    1.06
     within
    1.03
     anywhere
    0.97
     inside
    0.95
     outside
    0.90
    Act Density 0.107%

    No Known Activations