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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "through."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aken
    -0.16
    .grp
    -0.15
    ursal
    -0.14
    ÑĩÑĥ
    -0.14
     Ø°
    -0.14
    Ñıк
    -0.14
    ENSE
    -0.13
    ÑĪкÑĥ
    -0.13
    quette
    -0.13
    .plist
    -0.13
    POSITIVE LOGITS
    -out
    0.19
    put
    0.18
    ly
    0.18
    705
    0.17
    bred
    0.16
    INDER
    0.15
    whel
    0.15
    /in
    0.15
    enger
    0.15
    puts
    0.15
    Act Density 0.051%

    No Known Activations