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

    Neuronpedia

    INDEX
    Explanations

    references to circuits and circuitry in technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     esponja
    -0.52
     propOrder
    -0.49
     Sünde
    -0.47
     škoda
    -0.46
     idéia
    -0.45
     uș
    -0.45
     avoient
    -0.44
     błę
    -0.44
     segnale
    -0.44
     manual
    -0.44
    POSITIVE LOGITS
     circuit
    0.62
     mut
    0.62
     circuits
    0.60
     contra
    0.58
    mut
    0.57
    Contra
    0.56
     Contra
    0.54
     Circuit
    0.54
    contra
    0.53
     Circuits
    0.53
    Act Density 0.191%

    No Known Activations