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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the presence of important details or specific points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hazi
    -0.15
    efined
    -0.15
    urses
    -0.15
    recall
    -0.14
    ci
    -0.14
    urations
    -0.14
    aptop
    -0.14
    ington
    -0.14
     Vaults
    -0.14
    ych
    -0.14
    POSITIVE LOGITS
    693
    0.16
     Passage
    0.14
    abe
    0.14
    .sax
    0.14
    asher
    0.13
    iglia
    0.13
    ailer
    0.13
    495
    0.13
    argin
    0.13
    atto
    0.13
    Act Density 0.014%

    No Known Activations