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

    Neuronpedia

    INDEX
    Explanations

    references to hints or suggestions

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

    usage of the word 'hint'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WEBPACK
    -0.47
     للاسماء
    -0.43
     journées
    -0.39
     McGovern
    -0.39
    PhysRev
    -0.39
     Autom
    -0.39
    andaag
    -0.38
    )})
    -0.38
     
    -0.36
    ecma
    -0.36
    POSITIVE LOGITS
     hint
    2.14
     hints
    2.02
     Hints
    1.82
    hint
    1.77
     Hint
    1.74
    hints
    1.73
    Hints
    1.70
    Hint
    1.60
     hinting
    1.58
     hinted
    1.54
    Act Density 0.004%

    No Known Activations