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

    Neuronpedia

    INDEX
    Explanations

    phrases related to significant events or occurrences

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate occurrences and ongoing situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lex
    -0.70
    retty
    -0.67
    enture
    -0.67
    maxwell
    -0.65
    nered
    -0.64
     caution
    -0.64
    itches
    -0.63
    reau
    -0.62
    theless
    -0.61
    loo
    -0.60
    POSITIVE LOGITS
     heartbeat
    0.74
    verages
    0.72
     spawned
    0.69
     plag
    0.68
     underpin
    0.66
     Bulg
    0.64
    hest
    0.62
     presently
    0.62
    division
    0.61
     fundament
    0.61
    Act Density 0.280%

    No Known Activations