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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations represented by an equal sign followed by a numeric value

    oai_token-act-pair · gpt-3.5-turbo

    expressions of equality or mathematical equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itage
    -0.80
    wright
    -0.78
    eness
    -0.76
    chool
    -0.76
    grounds
    -0.75
    eding
    -0.74
    liner
    -0.73
    SPONSORED
    -0.72
    pring
    -0.72
    soDeliveryDate
    -0.72
    POSITIVE LOGITS
    ========
    1.74
    ============
    1.64
    ===
    1.26
     False
    0.94
    ãĥ´ãĤ¡
    0.86
    ãĥīãĥ©ãĤ´ãĥ³
    0.86
     TRUE
    0.85
     {}
    0.84
     FALSE
    0.84
     0
    0.83
    Act Density 0.016%

    No Known Activations