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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating success or effectiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ayacak
    -0.16
    ixer
    -0.15
    adox
    -0.15
    izr
    -0.15
     seriously
    -0.14
    deme
    -0.14
    Äĩi
    -0.14
    astro
    -0.14
    ipop
    -0.14
    eing
    -0.14
    POSITIVE LOGITS
    ī
    0.16
    uster
    0.14
    indr
    0.14
    imiters
    0.13
    klä
    0.13
    mouth
    0.13
    /high
    0.13
    autorelease
    0.13
    OptionPane
    0.13
     tutor
    0.13
    Act Density 0.035%

    No Known Activations