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

    Neuronpedia

    INDEX
    Explanations

    references to the word "with" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stem
    -0.91
    pring
    -0.83
    ulty
    -0.78
    Discuss
    -0.78
    onto
    -0.77
    icious
    -0.72
    æ©Ł
    -0.72
    clips
    -0.71
    orsi
    -0.69
    sylvania
    -0.69
    POSITIVE LOGITS
     whichever
    1.08
     whatever
    0.85
     precaution
    0.78
     whoever
    0.76
     caution
    0.75
     impunity
    0.74
     regards
    0.73
     instinct
    0.73
    stood
    0.70
     brute
    0.68
    Act Density 0.024%

    No Known Activations