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

    Neuronpedia

    INDEX
    Explanations

    phrases or expressions that convey methods or approaches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idel
    -0.18
    ruba
    -0.16
    opes
    -0.15
    kul
    -0.15
    å¹¹
    -0.14
    _BACKEND
    -0.14
    Fallback
    -0.14
    _VOICE
    -0.14
    inki
    -0.13
    /drivers
    -0.13
    POSITIVE LOGITS
    ži
    0.19
    олÑı
    0.15
     Snowden
    0.15
     suff
    0.15
    ippers
    0.14
     Moss
    0.14
    aways
    0.13
    živ
    0.13
    å£
    0.13
     Rena
    0.13
    Act Density 0.012%

    No Known Activations