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

    Neuronpedia

    INDEX
    Explanations

    phrases related to behind-the-scenes insights and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olen
    -0.16
    çĪ
    -0.16
    steen
    -0.15
    olan
    -0.15
    ochen
    -0.15
    edad
    -0.14
    laden
    -0.14
    dea
    -0.13
    ida
    -0.13
    enk
    -0.13
    POSITIVE LOGITS
     behind
    0.33
     Behind
    0.26
     insiders
    0.24
     inner
    0.23
     inside
    0.23
    Behind
    0.22
     processes
    0.22
     process
    0.21
     insider
    0.20
    åĨħéĥ¨
    0.20
    Act Density 0.162%

    No Known Activations