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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe the organization and presentation of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Specifier
    -0.15
    ansson
    -0.14
    /people
    -0.14
    ISE
    -0.14
    Cls
    -0.14
    è¦ĸ
    -0.14
    анд
    -0.13
    à¥ĭà¤ķर
    -0.13
    620
    -0.13
    spar
    -0.13
    POSITIVE LOGITS
     how
    0.20
     why
    0.16
    ogui
    0.16
    aoke
    0.16
     ways
    0.15
    .scalablytyped
    0.15
    æ¸ħæ¥ļ
    0.15
    ifact
    0.15
    iless
    0.15
    ennon
    0.15
    Act Density 0.052%

    No Known Activations