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

    Neuronpedia

    INDEX
    Explanations

    conditional statements regarding hypothetical scenarios

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements or hypothetical scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AMA
    -0.65
    foreseen
    -0.64
     adolesc
    -0.62
    usha
    -0.62
    Favorite
    -0.61
    ocations
    -0.58
     Checking
    -0.58
    GGGGGGGG
    -0.58
    iky
    -0.58
    ADE
    -0.57
    POSITIVE LOGITS
     surely
    1.30
     undoubtedly
    1.21
     doubtless
    1.19
     be
    1.15
     probably
    1.12
     likely
    1.08
     certainly
    1.05
     definitely
    1.01
     vanish
    0.99
     cease
    0.98
    Act Density 0.262%

    No Known Activations