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

    Neuronpedia

    INDEX
    Explanations

    punctuations and conjunctions to analyze sentence structure and flow

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gram
    -0.15
     Everest
    -0.15
     fusion
    -0.15
     Canter
    -0.14
     gate
    -0.14
     (~(
    -0.14
    arp
    -0.14
     McC
    -0.14
     gram
    -0.14
    achat
    -0.14
    POSITIVE LOGITS
    Ľ
    0.16
    ENE
    0.15
    ãĤ¿ãĥ«
    0.14
    UNET
    0.14
    HIR
    0.14
    hir
    0.14
    ëįĺ
    0.14
    agit
    0.14
    _behavior
    0.13
    judge
    0.13
    Act Density 0.005%

    No Known Activations