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

    Neuronpedia

    INDEX
    Explanations

    phrases related to future plans or potential opportunities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to potential candidates or situations involving expectation and possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kar
    -0.81
    lua
    -0.79
    ifting
    -0.72
    lain
    -0.71
    cart
    -0.71
    TOP
    -0.71
    anguages
    -0.68
    ahi
    -0.65
    lang
    -0.64
    FactoryReloaded
    -0.64
    POSITIVE LOGITS
     prospective
    0.95
     traject
    0.91
    spective
    0.91
     cohort
    0.85
     seekers
    0.85
     elig
    0.82
     buyers
    0.82
     trajectory
    0.79
     prospects
    0.79
     applicants
    0.77
    Act Density 0.008%

    No Known Activations