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

    Neuronpedia

    INDEX
    Explanations

    informational phrases starting with "here's what you need to know" or "here's what we know" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express knowledge or information about various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rys
    -0.78
    shoot
    -0.71
    phy
    -0.65
    erers
    -0.63
    prints
    -0.61
    zan
    -0.59
    erer
    -0.59
    aml
    -0.59
    ahime
    -0.57
    bris
    -0.57
    POSITIVE LOGITS
     about
    1.44
     ABOUT
    1.36
     regarding
    1.24
     About
    1.18
    about
    1.10
    About
    1.09
     concerning
    1.05
     bout
    0.91
     Regarding
    0.89
     pertaining
    0.86
    Act Density 0.107%

    No Known Activations