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

    Neuronpedia

    INDEX
    Explanations

    negative constructions and expressions of doubt or uncertainty

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     itſelf
    -0.82
     Cæsar
    -0.76
     greateſt
    -0.74
     Reſ
    -0.73
     faſt
    -0.71
     laſt
    -0.70
     Lithuan
    -0.69
    )}_
    -0.69
     unſ
    -0.69
    matically
    -0.68
    POSITIVE LOGITS
     want
    0.64
     BoxDecoration
    0.60
    ictwa
    0.60
     understand
    0.59
     know
    0.59
     FontWeight
    0.55
     believe
    0.55
    UpInside
    0.54
     are
    0.54
     care
    0.53
    Act Density 0.050%

    No Known Activations