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

    Neuronpedia

    INDEX
    Explanations

    words related to wearing or putting on something

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "don" as it relates to negation or refusal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EStreamFrame
    -0.75
     safegu
    -0.63
     retard
    -0.62
     pus
    -0.61
     learning
    -0.60
     adversaries
    -0.60
     exha
    -0.59
     buffet
    -0.59
     ejected
    -0.59
    anwhile
    -0.58
    POSITIVE LOGITS
    't
    1.72
    ned
    1.52
    ates
    1.25
    uts
    1.17
    ning
    1.15
    keys
    1.13
    nered
    1.01
    ated
    1.00
    eness
    0.99
    ate
    0.96
    Act Density 0.118%

    No Known Activations