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

    Neuronpedia

    INDEX
    Explanations

    phrases related to words that include the substring "des"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to degradation or diminishing quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    regor
    -0.79
    hetti
    -0.78
    glers
    -0.74
    razil
    -0.73
    OWS
    -0.73
    Reviewer
    -0.72
    ancial
    -0.72
    DAY
    -0.70
    zzi
    -0.68
    intendent
    -0.66
    POSITIVE LOGITS
    ync
    0.93
    erve
    0.93
    ugar
    0.88
    irable
    0.86
    plet
    0.84
    semb
    0.83
    ection
    0.83
    cipl
    0.82
    cend
    0.82
    ktop
    0.81
    Act Density 0.008%

    No Known Activations