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

    Neuronpedia

    INDEX
    Explanations

    time-related phrases or temporal contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote specific moments in time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uctions
    -0.74
    gements
    -0.74
    avorite
    -0.73
    rals
    -0.72
     chances
    -0.72
    ishers
    -0.67
    irm
    -0.65
     packages
    -0.64
    artments
    -0.63
     grounding
    -0.62
    POSITIVE LOGITS
    glass
    0.76
    adobe
    0.75
     Spiral
    0.70
    aign
    0.68
    cia
    0.67
    wcs
    0.67
    AZ
    0.66
    ={
    0.66
    ICA
    0.65
     fraught
    0.64
    Act Density 0.052%

    No Known Activations