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

    Neuronpedia

    INDEX
    Explanations

    keywords related to compatibility

    oai_token-act-pair · gpt-3.5-turbo

    terms related to compatibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vae
    -0.82
    vern
    -0.77
    mington
    -0.76
    arcity
    -0.74
    Downloadha
    -0.74
    otonin
    -0.73
    ghazi
    -0.70
    gary
    -0.70
    vard
    -0.68
    ²¾
    -0.68
    POSITIVE LOGITS
     compatibility
    0.89
    atibility
    0.86
     Compatibility
    0.81
     compatible
    0.77
    ably
    0.76
    ity
    0.74
    atible
    0.74
    ivity
    0.70
    iations
    0.70
    ities
    0.68
    Act Density 0.026%

    No Known Activations