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

    Neuronpedia

    INDEX
    Explanations

    negative sentiments or commentary about certain topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TagMode
    -0.59
     <>",
    -0.53
    UnusedPrivate
    -0.53
     HasFactory
    -0.51
     дописавши
    -0.49
     ewigen
    -0.49
     ***!
    -0.49
    UpInside
    -0.48
    ClientSize
    -0.47
    FieldOffset
    -0.47
    POSITIVE LOGITS
     what
    1.21
    everything
    1.17
     things
    1.16
     everything
    1.15
    THING
    1.14
     nothing
    1.14
    nothing
    1.13
    what
    1.09
    anything
    1.08
     anything
    1.07
    Act Density 0.510%

    No Known Activations