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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe simplicity or straightforwardness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    StoryboardSegue
    -0.46
    #+#
    -0.45
     einfach
    -0.44
    simply
    -0.43
    nalités
    -0.43
     protoimpl
    -0.41
    findpost
    -0.40
    adaptiveStyles
    -0.40
    simple
    -0.40
     specifically
    -0.40
    POSITIVE LOGITS
    minded
    0.80
    tons
    0.75
    ton
    0.73
     yet
    0.71
     minded
    0.61
     pleasures
    0.59
    mindedness
    0.56
     elegance
    0.55
    yet
    0.53
     enough
    0.52
    Act Density 0.185%

    No Known Activations