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

    Neuronpedia

    INDEX
    Explanations

    specific items or technologies that are being used or referenced in a given context

    oai_token-act-pair · gpt-3.5-turbo

    references to items or techniques that are utilized in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unexpected
    -0.68
    ihad
    -0.67
     unforeseen
    -0.65
    xious
    -0.65
     uncertain
    -0.64
    inventoryQuantity
    -0.64
     outwe
    -0.63
     spite
    -0.62
    bent
    -0.62
     curiosity
    -0.61
    POSITIVE LOGITS
     used
    0.85
     commonly
    0.81
    illac
    0.77
     Used
    0.77
     employed
    0.76
     onboard
    0.75
     standard
    0.73
     throughout
    0.72
     everywhere
    0.70
     nowadays
    0.68
    Act Density 0.296%

    No Known Activations