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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate purpose or intention

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

    for followed by noun phrase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.64
     BorderSide
    -0.56
     surtido
    -0.52
    httphttps
    -0.50
     garantías
    -0.49
     nakalista
    -0.47
     importación
    -0.44
    Autoritní
    -0.44
     męska
    -0.43
     Comprometido
    -0.42
    POSITIVE LOGITS
    appendTo
    0.47
    Styleable
    0.41
    füllung
    0.40
    compressed
    0.40
    OrEmpty
    0.38
    arek
    0.38
    󠁣
    0.37
     חיצוניים
    0.37
    ViewFeatures
    0.37
     Telegram
    0.36
    Act Density 0.015%

    No Known Activations