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

    Neuronpedia

    INDEX
    Explanations

    language related to technical or procedural descriptions

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

    Preceding "to" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    to + verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    abestanden
    -0.76
    EndInit
    -0.72
     Becoming
    -0.72
    Becoming
    -0.71
     étoient
    -0.70
    AutoScale
    -0.68
     étoit
    -0.68
     Efq
    -0.68
     Becomes
    -0.67
     ſen
    -0.67
    POSITIVE LOGITS
     use
    0.81
     using
    0.74
     introduce
    0.69
     create
    0.68
     employ
    0.65
    让
    0.64
     introducing
    0.63
     employing
    0.59
     allow
    0.59
     combine
    0.59
    Act Density 1.209%

    No Known Activations