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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal matters and government institutions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thood
    -0.73
    ienne
    -0.72
    Ò
    -0.71
    essen
    -0.69
    tumblr
    -0.66
    itud
    -0.66
    imi
    -0.65
    icia
    -0.64
    ceive
    -0.64
    aunder
    -0.64
    POSITIVE LOGITS
     slightest
    1.12
     strongest
    1.08
     vast
    1.06
     greatest
    1.04
     latter
    1.04
     biggest
    1.03
     majority
    1.01
     entire
    0.99
     easiest
    0.98
     simplest
    0.96
    Act Density 0.298%

    No Known Activations