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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing the outcome of situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asus
    -0.83
    gow
    -0.73
    shaw
    -0.72
     arsen
    -0.70
    antry
    -0.68
    icons
    -0.67
    cious
    -0.66
    visual
    -0.66
    adobe
    -0.65
    ffield
    -0.65
    POSITIVE LOGITS
     differently
    0.94
     alright
    0.85
     ¯
    0.79
     smoother
    0.79
     nicely
    0.78
     okay
    0.77
     somew
    0.73
     favour
    0.73
     horribly
    0.73
     anyway
    0.72
    Act Density 0.018%

    No Known Activations