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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a sense of location or direction

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    agers
    -0.35
    asted
    -0.34
    yi
    -0.33
    ATURE
    -0.33
     Doctrine
    -0.32
    ized
    -0.32
    ouf
    -0.32
    ets
    -0.32
    asting
    -0.32
     Nanto
    -0.31
    POSITIVE LOGITS
    abouts
    0.63
    upon
    0.47
    fore
    0.47
    sembly
    0.45
    soever
    0.43
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    0.43
    ij士
    0.43
    ipl
    0.41
    ngth
    0.41
    EStream
    0.40
    Act Density 10.280%

    No Known Activations