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

    Neuronpedia

    INDEX
    Explanations

    the word "At" indicating the beginning of a new section or thought

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    981
    -0.15
    rig
    -0.14
    ajaran
    -0.14
    strom
    -0.14
    GPL
    -0.14
    heimer
    -0.14
    è§Ĩ
    -0.14
    lings
    -0.14
    umat
    -0.14
    primir
    -0.13
    POSITIVE LOGITS
    rray
    0.15
    ari
    0.15
    arov
    0.15
    ufe
    0.15
    oucher
    0.14
    izik
    0.14
    -anchor
    0.14
    .generated
    0.14
    callable
    0.14
    iven
    0.14
    Act Density 0.043%

    No Known Activations