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

    Neuronpedia

    INDEX
    Explanations

    phrases related to quantities or statistics

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases related to enumeration or lists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imum
    -0.80
    itol
    -0.75
     kickoff
    -0.72
    anta
    -0.71
    vity
    -0.69
    TP
    -0.67
    udence
    -0.67
    INESS
    -0.66
    anton
    -0.65
    azi
    -0.65
    POSITIVE LOGITS
     sheltered
    1.02
     ready
    0.95
     insured
    0.95
    pared
    0.93
     unprotected
    0.91
     repaired
    0.89
     vetted
    0.88
     liberated
    0.87
     vaccinated
    0.86
    verified
    0.86
    Act Density 0.272%

    No Known Activations