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

    Neuronpedia

    INDEX
    Explanations

    years or time periods in a chronological context

    oai_token-act-pair · gpt-3.5-turbo

    specific years or dates mentioned in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Maker
    -0.61
    Mag
    -0.61
     astroph
    -0.55
    Assembly
    -0.55
    ACTION
    -0.54
     suscept
    -0.54
    needed
    -0.53
     chances
    -0.52
    ERY
    -0.52
    Fix
    -0.52
    POSITIVE LOGITS
     onwards
    1.60
     onward
    1.47
     inception
    0.94
     until
    0.87
     till
    0.87
     downwards
    0.80
     through
    0.76
     thru
    0.76
    arten
    0.74
    until
    0.73
    Act Density 0.085%

    No Known Activations