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

    Neuronpedia

    INDEX
    Explanations

    keywords related to political and financial discussions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    enthal
    -0.65
     LF
    -0.63
    OND
    -0.60
     (-
    -0.58
    CLOSE
    -0.55
    SPA
    -0.55
    Actor
    -0.54
    (_
    -0.54
     (>
    -0.54
    oir
    -0.54
    POSITIVE LOGITS
    into
    0.83
    since
    0.67
    because
    0.66
    inducing
    0.64
    without
    0.64
    depending
    0.64
    udeb
    0.64
    ilation
    0.64
    than
    0.64
    when
    0.63
    Act Density 1.400%

    No Known Activations