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

    Neuronpedia

    INDEX
    Explanations

    references to food or drinks that are pleasant to consume, particularly those that are easily enjoyable

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "pal" and its variants in various contexts, often relating to companionship or casual relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Annotations
    -0.71
    CDC
    -0.68
     Consent
    -0.68
    DERR
    -0.67
    ECH
    -0.67
    ãĥ¼ãĥĨãĤ£
    -0.67
    à¼
    -0.65
    REE
    -0.65
    VOL
    -0.65
    BOX
    -0.64
    POSITIVE LOGITS
    atable
    1.31
    atial
    1.10
    estine
    1.02
    adin
    0.99
    mares
    0.92
    mop
    0.87
    pit
    0.87
     pal
    0.85
    itive
    0.83
    ours
    0.82
    Act Density 0.012%

    No Known Activations