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

    Neuronpedia

    INDEX
    Explanations

    names of public figures or political events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     blender
    -0.70
     convict
    -0.66
     scrim
    -0.66
     bloom
    -0.65
     elim
    -0.65
     subdivision
    -0.65
     Assy
    -0.63
     Belfast
    -0.62
     Buenos
    -0.62
     Bulgarian
    -0.62
    POSITIVE LOGITS
    own
    1.02
    tsy
    0.95
    ï¸ı
    0.94
    tre
    0.91
    self
    0.91
    shall
    0.87
    iversary
    0.85
    s
    0.85
    ship
    0.84
    daughter
    0.84
    Act Density 0.190%

    No Known Activations