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

    Neuronpedia

    INDEX
    Explanations

    questions or statements requesting information or feedback

    oai_token-act-pair · gpt-3.5-turbo

    the word "what" and related inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    robe
    -0.71
    ulic
    -0.69
    raction
    -0.69
    ped
    -0.66
    stead
    -0.66
    ster
    -0.65
    ubs
    -0.65
    por
    -0.64
    enburg
    -0.63
    eer
    -0.63
    POSITIVE LOGITS
     happened
    1.13
    soever
    1.13
     happens
    1.09
     happ
    1.08
     kinds
    1.07
     sorts
    1.06
     transpired
    0.89
     redes
    0.88
     kind
    0.86
     else
    0.86
    Act Density 0.120%

    No Known Activations