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

    Neuronpedia

    INDEX
    Explanations

    linguistic elements that introduce or modify clauses, particularly prepositional phrases and conjunctive terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kazy
    -0.16
    anke
    -0.15
    anou
    -0.15
    igel
    -0.15
    iph
    -0.14
    iya
    -0.14
    starter
    -0.14
    kola
    -0.13
    aneous
    -0.13
    ие
    -0.13
    POSITIVE LOGITS
     together
    0.17
    upon
    0.16
     incident
    0.16
     upon
    0.15
     vin
    0.15
     versa
    0.14
    uhn
    0.14
    TexImage
    0.14
     depending
    0.14
     according
    0.14
    Act Density 0.026%

    No Known Activations