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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating logical conclusions or evidence-based reasoning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    expandindo
    -0.73
    gdx
    -0.70
    setVerticalGroup
    -0.69
     betweenstory
    -0.64
    ⓘ
    -0.63
    wpi
    -0.63
    ########.
    -0.63
    addComponent
    -0.60
    DataSnapshot
    -0.59
    NARR
    -0.58
    POSITIVE LOGITS
    '],
    0.47
    inerja
    0.45
     تانيه
    0.42
    itel
    0.41
     major
    0.41
     induction
    0.41
     rule
    0.41
     law
    0.41
     dynamic
    0.40
     rang
    0.40
    Act Density 0.451%

    No Known Activations