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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and symbols that indicate emphasis or separation in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iple
    -0.69
    ãĤ©
    -0.64
    ©¶æ
    -0.64
     NX
    -0.63
     mail
    -0.60
    iler
    -0.59
    orts
    -0.58
    usha
    -0.58
     Moines
    -0.58
     nood
    -0.58
    POSITIVE LOGITS
    particularly
    1.34
    especially
    1.34
    something
    1.25
    including
    1.25
     namely
    1.19
    even
    1.08
    thus
    1.03
    often
    1.00
    provided
    1.00
    which
    0.97
    Act Density 0.106%

    No Known Activations