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

    Neuronpedia

    INDEX
    Explanations

    expressions emphasizing intensity or strong emphasis

    oai_token-act-pair · gpt-3.5-turbo

    expressions emphasizing intensity or magnitude in descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BIL
    -0.81
    isSpecialOrderable
    -0.74
     volunt
    -0.70
    CONCLUS
    -0.69
    xtap
    -0.66
     wisely
    -0.65
    illary
    -0.65
    eka
    -0.65
    Dialog
    -0.64
    earcher
    -0.63
    POSITIVE LOGITS
     Bulldogs
    0.81
     Hulk
    0.69
    orld
    0.69
     Clown
    0.68
     Hydra
    0.67
    shit
    0.67
     Blumenthal
    0.66
    gling
    0.65
     fuckin
    0.64
     Gon
    0.63
    Act Density 0.183%

    No Known Activations