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

    Neuronpedia

    INDEX
    Explanations

    instances of sentences starting with 'it is' or 'it's', indicating evaluations or descriptions

    oai_token-act-pair · gpt-3.5-turbo

    structures indicating hypothetical or conditional situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.72
    Priv
    -0.67
     Management
    -0.65
    Ore
    -0.64
     Ratio
    -0.64
     Syndrome
    -0.62
    ++++
    -0.62
    imon
    -0.60
    assembly
    -0.59
    ulner
    -0.59
    POSITIVE LOGITS
    veland
    0.80
     consciously
    0.77
     passively
    0.68
     guessed
    0.67
     includ
    0.67
     chooses
    0.67
     preached
    0.66
     perceive
    0.65
     coasts
    0.65
     livest
    0.64
    Act Density 0.079%

    No Known Activations