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

    Neuronpedia

    INDEX
    Explanations

    references to professional work or tasks

    oai_token-act-pair · gpt-3.5-turbo

    references to care, support, and the quality of work in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ´ãĥ³
    -0.86
    cffffcc
    -0.85
    ãĤ¦ãĤ¹
    -0.69
    inate
    -0.69
    dry
    -0.66
    ascript
    -0.65
    isexual
    -0.65
    ingo
    -0.63
    Í
    -0.63
    artifacts
    -0.63
    POSITIVE LOGITS
     they
    1.08
     afforded
    1.00
     undertaken
    0.98
     he
    0.96
     she
    0.91
     we
    0.91
     offered
    0.81
     done
    0.80
     thrown
    0.80
     amassed
    0.79
    Act Density 0.522%

    No Known Activations