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

    Neuronpedia

    INDEX
    Explanations

    specific nouns and adjectives that describe entities or items related to energy, infrastructure, and food

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     anyone
    -0.28
     as
    -0.27
     I
    -0.27
     persons
    -0.27
    por
    -0.27
     Go
    -0.26
     any
    -0.24
    机
    -0.24
     very
    -0.24
     and
    -0.24
    POSITIVE LOGITS
    0.87
    RegressionTest
    0.82
    findpost
    0.81
    +#+#
    0.80
    脚注の使い方
    0.77
    tvguidetime
    0.72
    oa̍t
    0.71
    phazard
    0.69
     surla
    0.69
    󠁴
    0.68
    Act Density 0.641%

    No Known Activations