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

    Neuronpedia

    INDEX
    Explanations

    words related to technology, infrastructure, and industry

    oai_token-act-pair · gpt-3.5-turbo

    nouns related to various societal issues and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¸
    -0.63
    Synopsis
    -0.63
    ihara
    -0.56
    Published
    -0.54
    ESCO
    -0.53
     Hills
    -0.53
    forestation
    -0.52
    ãĥį
    -0.52
    jamin
    -0.51
    iversary
    -0.51
    POSITIVE LOGITS
     are
    1.49
     aren
    1.36
     were
    1.25
     ARE
    1.21
     have
    1.18
     weren
    1.16
     HAVE
    1.08
     abound
    1.08
     deserve
    1.07
     seem
    1.06
    Act Density 0.469%

    No Known Activations