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

    Neuronpedia

    INDEX
    Explanations

    words related to current events or status updates

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "now."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ascript
    -0.67
     Enhancement
    -0.65
    ieu
    -0.65
     Bastard
    -0.63
     Divinity
    -0.62
     Didn
    -0.62
    achev
    -0.59
    advertisement
    -0.59
     Alchemist
    -0.58
     Geh
    -0.57
    POSITIVE LOGITS
    adays
    1.41
    here
    1.24
    heres
    0.95
     resides
    0.88
     reside
    0.83
     realizes
    0.82
     firmly
    0.82
     belongs
    0.82
    aukee
    0.82
     awaits
    0.78
    Act Density 0.071%

    No Known Activations