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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to computer programming, especially concerning methods and functions

    oai_token-act-pair · gpt-3.5-turbo

    specific names or terms, particularly those associated with notable organizations, figures, or descriptors related to negative contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istani
    -0.92
    xon
    -0.84
    assic
    -0.84
    ando
    -0.79
    uton
    -0.75
    acers
    -0.74
    anza
    -0.72
    imates
    -0.70
    tun
    -0.68
    lake
    -0.67
    POSITIVE LOGITS
     lender
    0.76
    hips
    0.73
     dealings
    0.69
     lending
    0.68
     coh
    0.68
     glim
    0.67
    NESS
    0.67
     contestants
    0.67
     stake
    0.66
     lenders
    0.66
    Act Density 0.022%

    No Known Activations