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

    Neuronpedia

    INDEX
    Explanations

    congratulatory messages

    oai_token-act-pair · gpt-3.5-turbo

    references to congratulations and expressions of support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     IMAGES
    -0.70
    istic
    -0.68
    pmwiki
    -0.68
     hazards
    -0.63
    istically
    -0.62
    ãĥīãĥ©ãĤ´ãĥ³
    -0.61
     hypers
    -0.61
    ical
    -0.60
    cies
    -0.60
     Helm
    -0.60
    POSITIVE LOGITS
    regation
    1.61
    rats
    1.48
    regate
    1.44
    reg
    1.29
    ression
    1.29
    rat
    1.21
    ressive
    1.21
    resso
    1.20
    ratulations
    1.14
    rador
    1.06
    Act Density 0.052%

    No Known Activations