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

    Neuronpedia

    INDEX
    Explanations

    phrases related to projects or plans that are in progress or being developed

    oai_token-act-pair · gpt-3.5-turbo

    references to projects, developments, or initiatives that are in progress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iannopoulos
    -0.71
    uesday
    -0.66
    ometimes
    -0.65
    milo
    -0.64
    anned
    -0.64
    ongyang
    -0.62
    atto
    -0.61
    ancel
    -0.60
    arcity
    -0.59
    paio
    -0.59
    POSITIVE LOGITS
     notch
    0.72
     bandwagon
    0.72
     coffers
    0.71
    hole
    0.68
     Jah
    0.67
    elight
    0.66
    geist
    0.65
    FTWARE
    0.64
     leash
    0.62
     footsteps
    0.62
    Act Density 0.146%

    No Known Activations