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

    Neuronpedia

    INDEX
    Explanations

    phrases related to potential and possibility, particularly in hypothetical contexts

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

    be followed verb/adjective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.73
    devamını
    -0.53
    дневно
    -0.48
    Bibliograf
    -0.47
     AssemblyTitle
    -0.47
     Gland
    -0.46
    IntOverflow
    -0.46
    stdint
    -0.44
    stuff
    -0.43
    antası
    -0.43
    POSITIVE LOGITS
     the
    0.52
    ={({
    0.42
     some
    0.39
     uș
    0.38
     meilleure
    0.38
     critical
    0.37
     esimer
    0.36
     побо
    0.36
    )}-\
    0.36
     ben
    0.36
    Act Density 0.026%

    No Known Activations