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

    Neuronpedia

    INDEX
    Explanations

    patterns and sequences related to software development

    oai_token-act-pair · gpt-3.5-turbo

    keywords or phrases related to technology and digital topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wet
    -0.77
     claws
    -0.66
     retard
    -0.65
     rapt
    -0.63
     sculpt
    -0.62
     goalie
    -0.62
     fish
    -0.61
     rubber
    -0.61
     aromatic
    -0.61
     dece
    -0.60
    POSITIVE LOGITS
    ccording
    1.52
    Whether
    1.28
    Since
    1.28
    While
    1.27
    There
    1.26
    Although
    1.26
    Given
    1.26
    When
    1.25
    Before
    1.24
    Following
    1.24
    Act Density 0.164%

    No Known Activations