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

    Neuronpedia

    INDEX
    Explanations

    the presence of the word "is" and its variants in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PYX
    -0.77
     AssemblyCulture
    -0.72
     Shakspeare
    -0.71
    antMatchers
    -0.71
     Meksiku
    -0.66
     Shaksp
    -0.64
    SharedCtor
    -0.64
     itſelf
    -0.62
     themſelves
    -0.61
     MediatR
    -0.59
    POSITIVE LOGITS
     no
    1.20
     plenty
    1.19
     lots
    1.01
     nothing
    0.94
     room
    0.92
     some
    0.84
     ample
    0.82
     enough
    0.81
     a
    0.81
     tons
    0.80
    Act Density 0.151%

    No Known Activations