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

    Neuronpedia

    INDEX
    Explanations

    references to recent events or occurrences

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "recent" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    claimer
    -0.91
    umes
    -0.76
    wright
    -0.75
    amina
    -0.75
    afort
    -0.74
    ealing
    -0.74
     presently
    -0.73
    requires
    -0.72
    utm
    -0.70
    anding
    -0.69
    POSITIVE LOGITS
     spate
    1.01
     additions
    0.97
     arrivals
    0.96
     developments
    0.94
     arrival
    0.86
     uptick
    0.85
     revelations
    0.83
     episode
    0.81
     afternoon
    0.80
     morning
    0.79
    Act Density 0.028%

    No Known Activations