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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating deprivation or loss of rights and privileges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     blij
    -0.59
     Altman
    -0.59
    ibald
    -0.56
    طقة
    -0.54
    piecze
    -0.50
    Adapters
    -0.49
     fiabilité
    -0.49
    ZIONI
    -0.48
     lämp
    -0.48
    yelidikan
    -0.48
    POSITIVE LOGITS
     blocking
    0.77
     Interference
    0.75
     obstruct
    0.75
     interference
    0.74
     Blocking
    0.72
     interfering
    0.72
     obstructed
    0.71
    AutoresizingMask
    0.71
     blocker
    0.71
     BLOCK
    0.69
    Act Density 0.515%

    No Known Activations