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

    Neuronpedia

    INDEX
    Explanations

    phrases related to progress or change towards modernization or automation

    oai_token-act-pair · gpt-3.5-turbo

    symbols or punctuation used in dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hement
    -0.81
    tons
    -0.77
     charm
    -0.76
     honoured
    -0.65
     endeav
    -0.64
     princ
    -0.64
     flare
    -0.63
     backbone
    -0.62
     precaution
    -0.62
    cules
    -0.61
    POSITIVE LOGITS
    ³³³
    0.85
    pmwiki
    0.78
    è¦ļéĨĴ
    0.78
     Reconstruction
    0.77
    ãĤ¦ãĤ¹
    0.74
    Narr
    0.74
    ↵Âł
    0.72
     âĨij
    0.70
    =-=-=-=-
    0.70
    galitarian
    0.70
    Act Density 0.226%

    No Known Activations