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

    Neuronpedia

    INDEX
    Explanations

    phrases related to describing a method or manner in which something is done

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe actions or phenomena associated with "the way" something is done or experienced

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     livest
    -0.88
    oppable
    -0.79
    emies
    -0.76
    usters
    -0.74
    ĸļ
    -0.72
     mathemat
    -0.71
    iasco
    -0.70
    cffff
    -0.70
    igh
    -0.70
    oubtedly
    -0.68
    POSITIVE LOGITS
    ward
    1.12
     forward
    0.93
    fare
    0.92
     Forward
    0.80
     Europeans
    0.79
     things
    0.76
    forward
    0.76
    point
    0.75
     they
    0.75
    finding
    0.75
    Act Density 0.046%

    No Known Activations