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

    Neuronpedia

    INDEX
    Explanations

    time-related contexts or actions

    oai_token-act-pair · gpt-3.5-turbo

    the term "ago" used in temporal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     suspic
    -0.86
     mathemat
    -0.86
     plaus
    -0.80
     tremend
    -0.79
     glim
    -0.76
     belie
    -0.75
     mobility
    -0.75
    lining
    -0.74
     challeng
    -0.73
     illumination
    -0.71
    POSITIVE LOGITS
    vernment
    1.42
    zzi
    1.08
    xon
    1.01
    onga
    0.97
    zzo
    0.94
    etta
    0.94
    ago
    0.90
    edia
    0.85
    asca
    0.84
    allo
    0.84
    Act Density 0.014%

    No Known Activations