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

    Neuronpedia

    INDEX
    Explanations

    dates written with numeric day and month followed by a city, often indicating the location and time of a news event

    oai_token-act-pair · gpt-3.5-turbo

    parenthetical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Advertisement
    -0.57
    ridge
    -0.57
     butcher
    -0.57
     consideration
    -0.55
     breeds
    -0.54
    #$#$
    -0.53
     establishments
    -0.52
     haun
    -0.52
     âĸĪ
    -0.52
     Misty
    -0.52
    POSITIVE LOGITS
    IPS
    0.86
     REUTERS
    0.81
    FIL
    0.77
    AFP
    0.74
    ãĥĻ
    0.69
    quickShipAvailable
    0.68
    env
    0.68
    GL
    0.68
    PI
    0.67
    UTC
    0.67
    Act Density 0.031%

    No Known Activations