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

    Neuronpedia

    INDEX
    Explanations

    structured data or code snippets related to programming or technical descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     számára
    -0.71
     Normdatei
    -0.61
    ledem
    -0.58
     dàng
    -0.54
     "];
    -0.54
     betreft
    -0.54
    reiras
    -0.53
     SIMBAD
    -0.53
    ."],
    -0.53
     gehouden
    -0.52
    POSITIVE LOGITS
     thing
    0.74
     wrong
    0.66
     Pascual
    0.62
     shit
    0.60
     piss
    0.60
     fucked
    0.58
     scape
    0.58
     funny
    0.57
     burnt
    0.57
     beginnetje
    0.57
    Act Density 0.203%

    No Known Activations