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

    Neuronpedia

    INDEX
    Explanations

    verbs related to increasing or decreasing

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to scaling or adjusting operations, particularly in context of reduction or increase

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iol
    -0.77
    cu
    -0.75
    pie
    -0.70
    Û
    -0.69
    pelled
    -0.67
    tainment
    -0.66
    ب
    -0.65
    PLIED
    -0.65
    Anne
    -0.63
    Kin
    -0.63
    POSITIVE LOGITS
    grading
    0.87
     erosion
    0.75
    graded
    0.75
     boosters
    0.74
    gradation
    0.72
    packs
    0.69
     enrollment
    0.69
     deforestation
    0.69
     effectiveness
    0.69
     maturity
    0.68
    Act Density 0.062%

    No Known Activations