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

    Neuronpedia

    INDEX
    Explanations

    references to parental figures and family relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itself
    -0.91
     itself
    -0.82
     itſelf
    -0.78
     Itself
    -0.76
    themselves
    -0.76
    UnsafeEnabled
    -0.72
     themſelves
    -0.69
     kasarigan
    -0.67
     transfieras
    -0.64
    évaluateur
    -0.64
    POSITIVE LOGITS
     who
    0.67
     whom
    0.60
    ’
    0.56
    Personendaten
    0.55
    AccessorTable
    0.54
     biologique
    0.54
    atial
    0.53
    '
    0.51
    Välislingid
    0.50
    
    0.49
    Act Density 0.181%

    No Known Activations