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

    Neuronpedia

    INDEX
    Explanations

    names and titles related to leadership and governmental positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     BoxFit
    -0.91
     betweenstory
    -0.81
     الحره
    -0.79
    zle
    -0.68
     дописавши
    -0.67
    PhysRev
    -0.67
    IsMutable
    -0.65
    ("$.
    -0.64
    copg
    -0.64
     reductase
    -0.62
    POSITIVE LOGITS
    Alabama
    0.65
    ⓧ
    0.64
    kuuta
    0.61
     Alabama
    0.59
    FSC
    0.49
     UAB
    0.48
     Welsh
    0.48
    Birmingham
    0.46
     Albanian
    0.46
    gdx
    0.46
    Act Density 0.242%

    No Known Activations