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

    Neuronpedia

    INDEX
    Explanations

    words expressing strong positive or emotional sentiments

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

    adverbs of manner and intensity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     atheists
    -0.56
    Muse
    -0.56
    IntoConstraints
    -0.55
     समीक्षाओं
    -0.53
    berdayakan
    -0.52
     assholes
    -0.51
    DockStyle
    -0.50
    Dichloropropene
    -0.50
     Muller
    -0.50
     AppComponent
    -0.49
    POSITIVE LOGITS
     dearly
    1.89
     sorely
    0.75
     desperately
    0.61
     greatly
    0.50
     loved
    0.49
     truly
    0.46
     clearly
    0.46
     urgently
    0.44
     fondly
    0.44
     dearest
    0.44
    Act Density 0.002%

    No Known Activations