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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or processes

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "about" indicating discussions or explanations of various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Amos
    -0.69
     Sharp
    -0.68
     Sung
    -0.66
     Mush
    -0.64
     Chang
    -0.63
     Jung
    -0.63
     Gat
    -0.62
     quote
    -0.62
    chens
    -0.62
     Hold
    -0.61
    POSITIVE LOGITS
    doms
    0.81
     Seym
    0.79
    ional
    0.79
    anchester
    0.78
     halfway
    0.75
    EStream
    0.75
    ortion
    0.73
     convol
    0.72
    MpServer
    0.72
    inel
    0.71
    Act Density 0.028%

    No Known Activations