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

    Neuronpedia

    INDEX
    Explanations

    time references in the format of "hour:minute p.m."

    oai_token-act-pair · gpt-3.5-turbo

    the letter "m" at various frequencies and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     behav
    -0.77
    schild
    -0.73
     recre
    -0.64
     ãĤµ
    -0.62
     Behavior
    -0.61
    tan
    -0.60
     Toast
    -0.58
     dwarves
    -0.58
    avorite
    -0.57
     performed
    -0.56
    POSITIVE LOGITS
     EDT
    1.04
    .,
    1.02
    obiles
    0.91
    endment
    0.87
     EST
    0.87
    .:
    0.86
    .;
    0.85
    oses
    0.85
    igr
    0.85
    iles
    0.84
    Act Density 0.019%

    No Known Activations