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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating acquisition or obtaining

    oai_token-act-pair · gpt-3.5-turbo

    the word "got" indicating events or actions experienced by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPONSORED
    -0.77
     depiction
    -0.70
    iege
    -0.66
     confines
    -0.63
    Ale
    -0.63
    ibel
    -0.61
     Alic
    -0.60
    allows
    -0.60
     Archdemon
    -0.58
    ively
    -0.58
    POSITIVE LOGITS
     rid
    1.18
    ãĥ³ãĤ¸
    0.87
    cha
    0.87
    zl
    0.75
    cloneembedreportprint
    0.73
    DragonMagazine
    0.73
     acquainted
    0.73
    terson
    0.73
     bitten
    0.72
     precedence
    0.72
    Act Density 0.052%

    No Known Activations