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

    Neuronpedia

    INDEX
    Explanations

    references to metaphors and figurative language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AccessException
    -0.17
    iosity
    -0.16
    tlement
    -0.16
    uled
    -0.15
    wich
    -0.15
    εÏĦ
    -0.15
    Disappear
    -0.15
    ÏĦιν
    -0.15
    меÑĤÑĮ
    -0.15
    rada
    -0.15
    POSITIVE LOGITS
     analogy
    0.16
    celik
    0.15
     Woodward
    0.15
    ynth
    0.14
    .INSTANCE
    0.14
    astos
    0.14
     Guth
    0.14
    575
    0.14
     Tal
    0.13
    anvas
    0.13
    Act Density 0.035%

    No Known Activations