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

    Neuronpedia

    INDEX
    Explanations

    features and specifications of a versatile flashlight

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hir
    -0.17
    uzzi
    -0.17
    agi
    -0.15
    _lazy
    -0.14
    lazy
    -0.14
     emb
    -0.14
    ssi
    -0.14
    -animate
    -0.14
    átek
    -0.13
    ibus
    -0.13
    POSITIVE LOGITS
     flashlight
    0.30
     torch
    0.28
    torch
    0.25
     Cree
    0.23
     tail
    0.23
     beam
    0.23
    /Runtime
    0.22
     Beam
    0.22
     Torch
    0.22
     Tail
    0.22
    Act Density 0.010%

    No Known Activations