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

    Neuronpedia

    INDEX
    Explanations

    instances of seeing or noticing actions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    PreferredItem
    -0.85
    Clik
    -0.80
     HasFactory
    -0.74
     Infórmanos
    -0.73
    featureID
    -0.69
     MessageBoxIcon
    -0.67
     reaſon
    -0.65
     limes
    -0.65
     Monfieur
    -0.64
    PerformLayout
    -0.63
    POSITIVE LOGITS
    لاثة
    0.58
     AB
    0.55
     Alex
    0.53
    uable
    0.53
    älter
    0.49
    我自己
    0.47
     can
    0.47
     sp
    0.46
     IV
    0.45
     
    0.45
    Act Density 0.018%

    No Known Activations