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

    Neuronpedia

    INDEX
    Explanations

    words related to journalism and reporters

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ament
    -0.78
    draw
    -0.64
    iments
    -0.63
    onz
    -0.62
    tons
    -0.62
    âķIJ
    -0.62
    ²
    -0.62
    --------------------------------------------------------
    -0.61
    redits
    -0.60
    ood
    -0.60
    POSITIVE LOGITS
     reporter
    3.55
     journalist
    2.41
     Reporter
    2.34
     correspondent
    2.26
     reporters
    2.14
     columnist
    1.88
     photographer
    1.81
     interviewer
    1.79
     journalists
    1.73
     writer
    1.73
    Act Density 0.015%

    No Known Activations