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

    Neuronpedia

    INDEX
    Explanations

    verbs that indicate changes in physical properties or conditions

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

    making things more or less

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Slf
    -0.67
    Parcelize
    -0.66
    ioutil
    -0.61
     []:
    -0.59
    execSQL
    -0.59
    \{\\
    -0.58
    tasche
    -0.57
    __;
    -0.57
    dafx
    -0.56
    ($__
    -0.56
    POSITIVE LOGITS
    strengthen
    0.92
     strengthen
    0.83
     Strengthen
    0.81
    Strengthen
    0.81
    ening
    0.79
     lengthen
    0.76
     harden
    0.74
    ened
    0.73
     lengthening
    0.73
     Strengthening
    0.71
    Act Density 0.018%

    No Known Activations