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

    Neuronpedia

    INDEX
    Explanations

    words related to time and progress

    oai_token-act-pair · gpt-3.5-turbo

    information related to funding or financial contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¿½
    -0.73
     dishon
    -0.71
     falsehood
    -0.66
     shorthand
    -0.66
     poorer
    -0.66
     rebuke
    -0.65
    ptoms
    -0.65
     disson
    -0.64
    inctions
    -0.63
     inept
    -0.63
    POSITIVE LOGITS
     plans
    1.30
     Plans
    1.18
     planned
    1.16
     upcoming
    1.16
     intend
    1.13
     rumored
    1.08
     intends
    1.06
     anticipate
    1.05
     slated
    1.03
     hopes
    1.02
    Act Density 0.923%

    No Known Activations