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

    Neuronpedia

    INDEX
    Explanations

    temporal phrases indicating recurring actions or events

    oai_token-act-pair · gpt-3.5-turbo

    phrases that reference specific time periods or moments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    terday
    -0.67
    MET
    -0.67
    ertodd
    -0.63
    liction
    -0.62
    cipline
    -0.60
     Ing
    -0.58
    ATHER
    -0.58
    rored
    -0.58
    NESS
    -0.57
    PB
    -0.57
    POSITIVE LOGITS
     onwards
    0.92
     perspective
    0.86
     standpoint
    0.86
     onward
    0.84
     perspectives
    0.72
    ratch
    0.72
    orum
    0.70
     outset
    0.69
     inception
    0.68
    users
    0.67
    Act Density 0.027%

    No Known Activations