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

    Neuronpedia

    INDEX
    Explanations

    negative sentiments or critical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Roskov
    -0.61
    tagHelper
    -0.51
    Chham
    -0.50
    konzert
    -0.45
    perror
    -0.45
    ไง
    -0.44
    انگلیسی
    -0.43
    ;"></
    -0.42
     hozz
    -0.42
    libft
    -0.41
    POSITIVE LOGITS
    ​—
    0.96
    UserScript
    0.89
     ujednoznacz
    0.88
    —
    0.85
    — 
    0.83
    verwijspagina
    0.80
    ?—
    0.79
    )—
    0.76
    はじめに
    0.76
    ,—
    0.75
    Act Density 0.298%

    No Known Activations