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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing certainty or perception

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "tell" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Contents
    -0.73
    heres
    -0.70
    pmwiki
    -0.64
    rences
    -0.63
    BLE
    -0.60
    theless
    -0.60
    lique
    -0.59
    entials
    -0.59
    uga
    -0.58
    imposed
    -0.58
    POSITIVE LOGITS
    tale
    1.04
     apart
    0.78
    ingly
    0.71
     anecd
    0.68
    uyomi
    0.65
    eret
    0.64
     instinctively
    0.63
     MPG
    0.62
     us
    0.62
     ya
    0.61
    Act Density 0.039%

    No Known Activations