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

    Neuronpedia

    INDEX
    Explanations

    technical terms and indicators related to data structures and programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tal
    -0.72
    t
    -0.71
    ter
    -0.70
    U
    -0.70
    co
    -0.70
    ton
    -0.69
    式
    -0.69
    ty
    -0.69
    the
    -0.67
    to
    -0.66
    POSITIVE LOGITS
    ſelves
    1.10
    Jaunes
    1.07
    citenamefont
    1.01
     '\\;'
    0.98
    hips
    0.97
    ingtones
    0.93
    helves
    0.93
     doubtnut
    0.93
    BibitemShut
    0.92
     saites
    0.92
    Act Density 4.189%

    No Known Activations