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

    Neuronpedia

    INDEX
    Explanations

    graphical elements and data representations in research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shm
    -0.18
    /cop
    -0.15
    raith
    -0.15
    åIJįçĦ¡ãģĹ
    -0.15
     zem
    -0.15
    allis
    -0.14
    istence
    -0.14
    jeme
    -0.14
    beg
    -0.14
    .poly
    -0.14
    POSITIVE LOGITS
    ik
    0.16
    er
    0.15
    itive
    0.15
    arg
    0.14
     Argument
    0.14
    VO
    0.14
    ovo
    0.14
    r
    0.14
     Glas
    0.14
    _weak
    0.14
    Act Density 0.005%

    No Known Activations