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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating inclusivity or universality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NVIC
    -0.41
     doInBackground
    -0.40
     IMC
    -0.40
     kohdetta
    -0.38
    SR
    -0.38
    PCM
    -0.38
    shund
    -0.37
    __((
    -0.36
     Strap
    -0.36
     ira
    -0.36
    POSITIVE LOGITS
    antMatchers
    0.64
    stylers
    0.58
    évaluateur
    0.52
     gewöhnlich
    0.51
     generaciones
    0.50
     fleste
    0.49
     rallado
    0.48
    masing
    0.48
    Składniki
    0.48
     Cualquier
    0.47
    Act Density 0.518%

    No Known Activations