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

    Neuronpedia

    INDEX
    Explanations

    conjunctions within phrases or sentences

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    kefeller
    -0.76
    adr
    -0.69
    2020
    -0.67
    Explore
    -0.66
    Experts
    -0.65
    Prosecutors
    -0.65
    enter
    -0.64
    anza
    -0.64
    eers
    -0.64
    atom
    -0.63
    POSITIVE LOGITS
     I
    1.32
     my
    1.29
     myself
    1.15
     honestly
    1.08
     haha
    1.01
     thats
    0.98
     luckily
    0.96
     hindsight
    0.93
    I
    0.92
     THANK
    0.91
    Act Density 0.510%

    No Known Activations