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

    Neuronpedia

    INDEX
    Explanations

    statements or opinions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal or collective viewpoints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ammy
    -0.72
    isol
    -0.71
    glomer
    -0.68
    andise
    -0.67
    vernment
    -0.66
     earthqu
    -0.65
     dust
    -0.63
    ilant
    -0.63
    iott
    -0.62
    resist
    -0.61
    POSITIVE LOGITS
    finder
    1.15
     views
    0.93
    ports
    0.87
    points
    0.86
    ĸ
    0.82
     view
    0.81
    opian
    0.79
    port
    0.79
     viewpoint
    0.77
    ership
    0.77
    Act Density 0.030%

    No Known Activations