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

    Neuronpedia

    INDEX
    Explanations

    instances of conjunctions and connectives within the text

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

    "and" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    and followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     raping
    -0.53
    IUrlHelper
    -0.51
     ripple
    -0.50
     culminating
    -0.49
    ClCompile
    -0.47
    luste
    -0.47
     flagrant
    -0.46
     NDL
    -0.45
     IMMEDIATE
    -0.45
     mixtures
    -0.44
    POSITIVE LOGITS
     has
    0.76
     isKindOfClass
    0.68
     الرياضيه
    0.68
     have
    0.66
     had
    0.66
    脚注の使い方
    0.66
     otomatig
    0.63
    Vidite
    0.63
    ]--;
    0.61
     will
    0.61
    Act Density 0.566%

    No Known Activations