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

    Neuronpedia

    INDEX
    Explanations

    mentions of news and social media engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oren
    -0.18
    âĢ¦↵
    -0.15
    andi
    -0.15
    ¬Ĥ
    -0.14
    endl
    -0.14
    âĢ¦
    -0.14
     w
    -0.14
     Bin
    -0.13
    äch
    -0.13
    orex
    -0.13
    POSITIVE LOGITS
    .Subscribe
    0.19
    macros
    0.17
    arel
    0.16
    订
    0.16
     handjob
    0.15
     Microsystems
    0.15
    subscription
    0.15
     subscription
    0.15
    رÙĤ
    0.15
    unsubscribe
    0.14
    Act Density 0.055%

    No Known Activations