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

    Neuronpedia

    INDEX
    Explanations

    references to subfolder structures in a directory or file system context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.18
    icks
    -0.17
    anja
    -0.16
     Asp
    -0.15
    ader
    -0.15
    ized
    -0.15
    us
    -0.15
     Raid
    -0.15
    ska
    -0.14
     Giles
    -0.14
    POSITIVE LOGITS
    ordinated
    0.25
    woo
    0.24
    ordin
    0.23
    ordinate
    0.22
    sume
    0.21
    suming
    0.20
    divide
    0.20
    mers
    0.19
    sum
    0.19
    nets
    0.19
    Act Density 0.018%

    No Known Activations