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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating unlikelihood or improbability

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating improbability or doubt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -0.84
    oola
    -0.79
    cience
    -0.75
    utterstock
    -0.74
    ravings
    -0.73
    ription
    -0.72
    ngth
    -0.72
    utations
    -0.71
    aeper
    -0.71
    rongh
    -0.71
    POSITIVE LOGITS
     ever
    0.85
    theless
    0.85
     anymore
    0.76
     Squirrel
    0.76
     EVER
    0.76
     anything
    0.75
    icably
    0.73
     coincidence
    0.72
    bably
    0.68
     anyone
    0.67
    Act Density 0.041%

    No Known Activations