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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    ready to act

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    toHexString
    -0.52
    Aholisi
    -0.47
     lack
    -0.44
     the
    -0.42
    medades
    -0.40
     mochilas
    -0.38
    Herkunft
    -0.37
     nė
    -0.35
     frequência
    -0.35
     particularly
    -0.35
    POSITIVE LOGITS
     Ready
    0.87
     ready
    0.84
    Ready
    0.84
     READY
    0.79
     siap
    0.78
    ready
    0.70
    READY
    0.69
     Гото
    0.69
     готов
    0.67
    Гото
    0.66
    Act Density 0.005%

    No Known Activations