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

    Neuronpedia

    INDEX
    Explanations

    phrases related to events or actions that happened after a specific trigger or cause

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "following."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aucas
    -0.81
    cci
    -0.80
    rimination
    -0.79
    eri
    -0.73
    ice
    -0.72
    iman
    -0.69
    cin
    -0.68
    acus
    -0.67
    orc
    -0.65
    adle
    -0.64
    POSITIVE LOGITS
     follows
    0.73
     SX
    0.72
    combe
    0.71
     weeks
    0.68
    ĸļ
    0.66
     ceremonies
    0.61
    >:
    0.60
     sessions
    0.60
     directions
    0.59
     week
    0.59
    Act Density 0.025%

    No Known Activations