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

    Neuronpedia

    INDEX
    Explanations

    suffixes that typically denote nouns or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kamp
    -0.75
    recomm
    -0.69
     Masquerade
    -0.68
    indal
    -0.64
     Tuc
    -0.64
    ONSORED
    -0.63
    \\\\\\\\
    -0.63
     Haram
    -0.63
     Wonderland
    -0.61
    CHAR
    -0.61
    POSITIVE LOGITS
    etary
    0.84
    cious
    0.81
    incial
    0.77
    hesive
    0.77
    ents
    0.74
    erity
    0.73
    phrine
    0.72
    nces
    0.72
    onial
    0.72
    perate
    0.71
    Act Density 0.011%

    No Known Activations