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

    Neuronpedia

    INDEX
    Explanations

    unanswered questions or uncertainties

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     simulator
    -0.64
     simul
    -0.55
     escort
    -0.53
     traverse
    -0.51
     tube
    -0.51
     canvas
    -0.51
     surplus
    -0.50
     pil
    -0.50
     accustomed
    -0.49
     tubes
    -0.48
    POSITIVE LOGITS
    given
    0.74
     Nonetheless
    0.67
    yet
    0.63
    ONSORED
    0.63
     Regardless
    0.62
     Nevertheless
    0.61
     Especially
    0.61
     Unless
    0.61
    unless
    0.59
    _>
    0.59
    Act Density 0.900%

    No Known Activations