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

    Neuronpedia

    INDEX
    Explanations

    numbers and mathematical symbols in a specific context

    oai_token-act-pair · gpt-3.5-turbo

    references to temporal or conditional phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     concess
    -0.50
     Lama
    -0.49
     equivalent
    -0.47
     outwe
    -0.47
     lever
    -0.47
     programmed
    -0.47
     bottleneck
    -0.46
     spearheaded
    -0.46
    abwe
    -0.46
     Jinping
    -0.45
    POSITIVE LOGITS
    OSP
    0.67
    lement
    0.65
    generic
    0.58
    gif
    0.55
    ieg
    0.54
    catentry
    0.54
    natureconservancy
    0.53
    OTOS
    0.53
    ISC
    0.53
    attery
    0.53
    Act Density 0.646%

    No Known Activations