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

    Neuronpedia

    INDEX
    Explanations

    highly frequent function words and conjunctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ests
    -0.17
    ugu
    -0.16
    ruk
    -0.15
    ãĤ¤ãĥ³ãĥĪ
    -0.15
    anggan
    -0.15
    .codes
    -0.15
    èĻ«
    -0.15
    KS
    -0.14
    hlen
    -0.14
    ks
    -0.14
    POSITIVE LOGITS
    립
    0.15
    icer
    0.15
     Zust
    0.14
    ì²ł
    0.14
    éĢ
    0.14
    opal
    0.14
    IBLE
    0.13
    ible
    0.13
    ial
    0.13
     STR
    0.13
    Act Density 0.001%

    No Known Activations