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

    Neuronpedia

    INDEX
    Explanations

    discussions regarding legal and regulatory frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stuff
    -0.87
     whatnot
    -0.78
     thingy
    -0.78
     pretty
    -0.76
     maybe
    -0.75
     somebody
    -0.75
     things
    -0.75
     crappy
    -0.74
     something
    -0.73
     Maybe
    -0.72
    POSITIVE LOGITS
     itſelf
    0.77
     raiſ
    0.73
    ℠
    0.71
     regionally
    0.71
     seamlessly
    0.70
     uniquely
    0.69
     neceff
    0.68
    ſelf
    0.68
    ®-
    0.66
     ſy
    0.65
    Act Density 0.596%

    No Known Activations