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

    Neuronpedia

    INDEX
    Explanations

    references to potential outcomes or possibilities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    XtraEditors
    -0.82
     Biscuits
    -0.81
     Biscuit
    -0.79
     Burrow
    -0.75
     Cister
    -0.72
     fermions
    -0.71
     biscuits
    -0.70
    hirts
    -0.70
     Pharisees
    -0.69
     Chy
    -0.69
    POSITIVE LOGITS
     potential
    1.32
     Potential
    1.30
    Potential
    1.24
     potentials
    1.11
     POTENTIAL
    1.09
    potential
    1.09
     potencial
    0.93
     potensi
    0.90
     potenciales
    0.86
     potenti
    0.84
    Act Density 0.065%

    No Known Activations