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

    Neuronpedia

    INDEX
    Explanations

    dates and specific time-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to days of the week and time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     flashback
    -0.58
     lux
    -0.58
     Scenes
    -0.57
    ++;
    -0.55
     nods
    -0.54
     pecul
    -0.53
     flashbacks
    -0.53
    }}}
    -0.52
     sparkling
    -0.52
     afar
    -0.52
    POSITIVE LOGITS
     toward
    0.86
     to
    0.86
    to
    0.85
    nih
    0.76
    ordering
    0.75
    uggest
    0.75
     towards
    0.74
    FML
    0.72
     ordering
    0.70
     whereby
    0.68
    Act Density 0.630%

    No Known Activations