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

    Neuronpedia

    INDEX
    Explanations

    entities or names ending in 'k'

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the letter 'k'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mosqu
    -0.81
     liberties
    -0.72
    phrine
    -0.68
     emergencies
    -0.68
     behavi
    -0.66
     commons
    -0.62
    ãĤ¬
    -0.62
     Marketable
    -0.61
     constitu
    -0.61
     clich
    -0.60
    POSITIVE LOGITS
    ansas
    1.31
    irk
    1.20
    idding
    1.16
    orea
    1.13
    rieg
    1.11
    ileaks
    1.03
    icker
    1.02
    alion
    0.98
    appa
    0.95
    itty
    0.95
    Act Density 0.046%

    No Known Activations