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

    Neuronpedia

    INDEX
    Explanations

    numerical and mathematical notation in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     feminists
    -0.58
     according
    -0.58
     astronomer
    -0.56
     astronomers
    -0.55
    according
    -0.54
     通常
    -0.53
    TabIndex
    -0.53
     Apoptosis
    -0.52
    Luckily
    -0.52
     spender
    -0.51
    POSITIVE LOGITS
     The
    1.02
    ագրություններ
    0.84
    oa̍t
    0.80
     An
    0.79
    Toward
    0.76
    Towards
    0.76
    The
    0.73
    Review
    0.70
    "])
    0.69
    ✨:
    0.69
    Act Density 0.357%

    No Known Activations