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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a significant change or shift in a situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate significant changes or impacts over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oided
    -0.74
     filib
    -0.67
     Alone
    -0.67
     Recomm
    -0.65
    vati
    -0.64
    itia
    -0.64
    agra
    -0.64
     recommendations
    -0.63
    owship
    -0.62
     Abortion
    -0.62
    POSITIVE LOGITS
     toll
    1.07
     downturn
    0.84
     surreal
    0.81
     Toll
    0.73
    arily
    0.70
     stride
    0.67
     twist
    0.67
     shudder
    0.67
     foothold
    0.67
     dimension
    0.66
    Act Density 0.134%

    No Known Activations