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

    Neuronpedia

    INDEX
    Explanations

    words related to reversal or versatility

    oai_token-act-pair · gpt-3.5-turbo

    the suffix "vers" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dahl
    -0.58
    OUT
    -0.57
     Thumbnails
    -0.56
    OPLE
    -0.55
     reper
    -0.55
    RAG
    -0.54
    QB
    -0.54
     Hasan
    -0.53
     Nightmares
    -0.53
    FORE
    -0.52
    POSITIVE LOGITS
    hip
    1.66
    iveness
    1.44
    atile
    1.41
    ions
    1.35
    ibility
    1.35
    ibilities
    1.33
    ibly
    1.33
    atility
    1.30
    ively
    1.27
    itivity
    1.23
    Act Density 0.084%

    No Known Activations