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

    Neuronpedia

    INDEX
    Explanations

    punctuation characters and markers indicating text division

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to comparison or alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    culosis
    -0.55
    anwhile
    -0.53
    emale
    -0.50
    代
    -0.49
     Royale
    -0.47
    ugu
    -0.47
    vertis
    -0.45
    ãĥ¼ãĥĨ
    -0.45
    orst
    -0.44
     pione
    -0.44
    POSITIVE LOGITS
    pmwiki
    0.57
    NetMessage
    0.54
    natureconservancy
    0.50
    rower
    0.46
     Speedway
    0.45
    ¶
    0.45
     embodiments
    0.44
     disclaim
    0.44
     Flavoring
    0.43
     philosophers
    0.42
    Act Density 2.272%

    No Known Activations