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

    Neuronpedia

    INDEX
    Explanations

    references to specific topics or subjects in conversations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     %).
    -0.70
    seamnă
    -0.68
    }{#
    -0.66
    %"),
    -0.63
    )}}{
    -0.59
    '){
    -0.58
     %),
    -0.58
     houſe
    -0.56
    ’).
    -0.56
     ""],
    -0.56
    POSITIVE LOGITS
     stuff
    0.75
     today
    0.71
    exact
    0.66
     demain
    0.66
     exact
    0.66
    曖昧さ回避
    0.63
     guy
    0.63
     before
    0.60
     anymore
    0.60
     shit
    0.60
    Act Density 0.172%

    No Known Activations