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

    Neuronpedia

    INDEX
    Explanations

    elements related to specific identifiers or codes, often pertaining to data structures or programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Tikang
    -1.02
     ―――――
    -0.82
     iconFacebook
    -0.81
    .";
    -0.76
     faſt
    -0.76
     Arxivat
    -0.76
     ་་
    -0.74
    〉
    -0.74
     agra
    -0.74
    }$​
    -0.74
    POSITIVE LOGITS
     Z
    0.99
    setH
    0.99
     P
    0.96
     M
    0.93
     K
    0.93
     O
    0.92
     W
    0.91
     V
    0.85
     L
    0.85
     G
    0.84
    Act Density 0.090%

    No Known Activations