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

    Neuronpedia

    INDEX
    Explanations

    instances of partial information or examples that indicate broader concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unker
    -0.16
    eyer
    -0.15
    isset
    -0.15
    roken
    -0.14
     Mell
    -0.14
    ano
    -0.14
     Grü
    -0.14
    ãģĹãģı
    -0.14
     Mall
    -0.14
    oller
    -0.14
    POSITIVE LOGITS
     fraction
    0.32
    åĨ°
    0.26
     only
    0.24
     tip
    0.24
     fractions
    0.24
     mere
    0.24
     ìĿ¼ë¶Ģ
    0.23
     merely
    0.23
     scratching
    0.22
     portion
    0.22
    Act Density 0.141%

    No Known Activations