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

    Neuronpedia

    INDEX
    Explanations

    phrases related to exploration and discovery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivari
    -0.68
    enforcement
    -0.65
    iah
    -0.65
    corn
    -0.63
    roll
    -0.63
    wait
    -0.62
    Die
    -0.61
    guard
    -0.61
     inval
    -0.61
    si
    -0.61
    POSITIVE LOGITS
     possibilities
    0.99
    ationally
    0.96
     avenues
    0.90
    ibly
    0.90
     feasibility
    0.88
    ively
    0.82
    nels
    0.81
     Horizons
    0.80
    ibility
    0.79
     themes
    0.79
    Act Density 0.047%

    No Known Activations