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

    Neuronpedia

    INDEX
    Explanations

    adjectives or verbs related to negative or critical descriptions

    oai_token-act-pair · gpt-3.5-turbo

    negative or critical descriptors and terms related to instability, risk, and concern

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     BMC
    -0.69
     Beetle
    -0.65
     Sph
    -0.64
     Masquerade
    -0.64
     Aires
    -0.62
     Bret
    -0.62
     Elves
    -0.61
     Mend
    -0.61
     Decker
    -0.61
     Wilde
    -0.60
    POSITIVE LOGITS
    ificantly
    1.25
    initely
    1.16
    actly
    1.08
    thora
    1.07
    withstanding
    1.06
    terday
    1.06
    ufficient
    1.06
    etheless
    1.05
    lihood
    1.04
    icious
    1.04
    Act Density 0.186%

    No Known Activations