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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "information" and related terms indicating details or resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ih
    -0.16
    ettel
    -0.15
    urch
    -0.15
    heiro
    -0.15
    çݲ
    -0.14
    ESH
    -0.14
    uteur
    -0.13
    pon
    -0.13
    acionales
    -0.13
    izr
    -0.13
    POSITIVE LOGITS
     specific
    0.18
     sake
    0.18
     purposes
    0.17
     about
    0.17
    -specific
    0.16
     Grad
    0.15
     email
    0.15
    Specific
    0.15
     including
    0.15
    443
    0.15
    Act Density 0.037%

    No Known Activations