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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparisons or contrasts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    
    -0.51
    skosten
    -0.47
    таратура
    -0.46
     bounded
    -0.43
    nloa
    -0.42
    horabuena
    -0.42
     transmembrane
    -0.42
    adpleegd
    -0.42
    Allora
    -0.41
     authorized
    -0.39
    POSITIVE LOGITS
     Etc
    0.83
     whatnot
    0.82
     etc
    0.80
    Etc
    0.74
    etc
    0.68
    ETC
    0.66
    Населення
    0.66
     blah
    0.64
    — 
    0.63
    HtmlAttribute
    0.63
    Act Density 0.247%

    No Known Activations