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

    Neuronpedia

    INDEX
    Explanations

    words indicating majority or commonality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     houſe
    -0.55
     ſtate
    -0.51
    URLConnection
    -0.51
     ſever
    -0.51
     pleaſure
    -0.49
    unistd
    -0.49
    AutoModerator
    -0.49
    ISODE
    -0.48
     Banten
    -0.48
    WriteAttribute
    -0.47
    POSITIVE LOGITS
     mainly
    1.34
     primarily
    1.30
     Mainly
    1.21
     Mostly
    1.20
     chiefly
    1.20
     mostly
    1.19
    Mostly
    1.16
    mainly
    1.14
    Mainly
    1.13
     Primarily
    1.13
    Act Density 0.323%

    No Known Activations