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

    Neuronpedia

    INDEX
    Explanations

    repeated references to cycles in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     bureaus
    -0.76
     Asbury
    -0.75
     bureaux
    -0.73
     cytokines
    -0.69
     Guilford
    -0.69
     McQu
    -0.66
    RegistryLite
    -0.64
     metropolitana
    -0.64
     bursa
    -0.63
     ciphertext
    -0.63
    POSITIVE LOGITS
     cycle
    1.03
     CYCLE
    0.97
     Cycle
    0.96
    Cycle
    0.96
     cycles
    0.95
    cycle
    0.94
     ciclo
    0.89
     ciclos
    0.82
    cycles
    0.81
    ycle
    0.79
    Act Density 0.016%

    No Known Activations