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

    Neuronpedia

    INDEX
    Explanations

    phrases related to making selections or choices

    oai_token-act-pair · gpt-3.5-turbo

    instructions related to creating or managing lists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onement
    -0.66
    obl
    -0.64
     externalToEVAOnly
    -0.63
    ONG
    -0.62
    vind
    -0.62
    Enhanced
    -0.61
    cel
    -0.61
    olt
    -0.61
    ãĥĦ
    -0.61
    izophren
    -0.60
    POSITIVE LOGITS
     each
    1.14
     which
    1.07
     keywords
    1.06
     everything
    1.04
     names
    1.03
     favorites
    1.01
     categories
    1.00
     EVERY
    1.00
     what
    0.98
     whom
    0.98
    Act Density 0.298%

    No Known Activations