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

    Neuronpedia

    INDEX
    Explanations

    percentages or numerical changes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to statistical changes in crime rates or other measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     staples
    -0.68
    MET
    -0.62
    rich
    -0.62
    PAR
    -0.61
     nanop
    -0.59
    NRS
    -0.57
     dile
    -0.56
     essentials
    -0.56
     muster
    -0.56
    amina
    -0.56
    POSITIVE LOGITS
    xual
    1.05
    over
    0.96
    ait
    0.79
    itures
    0.76
     rate
    0.74
    overs
    0.73
    ulative
    0.73
    eful
    0.72
    iture
    0.72
    inth
    0.71
    Act Density 0.087%

    No Known Activations