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

    Neuronpedia

    INDEX
    Explanations

    phrases related to financial transactions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to conditions and opportunities for participation or success

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etsk
    -0.76
    monton
    -0.63
    berra
    -0.63
    dyl
    -0.61
    auga
    -0.60
     grooming
    -0.60
    inding
    -0.59
    uster
    -0.58
    olulu
    -0.58
     comb
    -0.57
    POSITIVE LOGITS
     WITH
    1.64
     THERE
    1.63
     THEIR
    1.62
     ABOUT
    1.57
     THESE
    1.57
     THIS
    1.56
     THE
    1.56
     THEY
    1.55
     THAT
    1.53
     SOME
    1.51
    Act Density 0.338%

    No Known Activations