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

    Neuronpedia

    INDEX
    Explanations

    Words and phrases expressing beliefs, actions, and consequences related to moral or ethical considerations

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

    accidentally knocking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ſelves
    -0.68
    DockStyle
    -0.65
    RegressionTest
    -0.60
    ſelf
    -0.59
    providedIn
    -0.58
    MLLoader
    -0.58
    ↹
    -0.55
     Houſe
    -0.54
    SaveVideo
    -0.53
    MemoryWarning
    -0.52
    POSITIVE LOGITS
     hacerlo
    0.56
     bunu
    0.54
     melakukannya
    0.54
     farlo
    0.46
     sitesinde
    0.40
     bunun
    0.38
    これは
    0.38
     acesta
    0.37
    一定
    0.37
    merkungen
    0.37
    Act Density 0.066%

    No Known Activations