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

    Neuronpedia

    INDEX
    Explanations

    instances where a significant amount or level of something is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    the emphasis on the word "much" and its variations to convey degrees of intensity or quantity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipe
    -0.71
    umbn
    -0.67
    ubs
    -0.67
    thumbnails
    -0.66
    imens
    -0.65
    YN
    -0.64
    scripts
    -0.63
    wat
    -0.63
    izen
    -0.62
    roots
    -0.62
    POSITIVE LOGITS
    OTAL
    0.69
     anymore
    0.65
    bang
    0.64
     advertised
    0.59
     mattered
    0.58
     Guinness
    0.58
     Ballard
    0.58
     disson
    0.58
     regardless
    0.56
    ange
    0.55
    Act Density 0.090%

    No Known Activations