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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize personal pronouns and expressions of self-reference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     himſelf
    -0.69
     itſelf
    -0.69
     Cæsar
    -0.68
    valget
    -0.64
     themſelves
    -0.63
     Poplar
    -0.60
     TTS
    -0.57
     Barnabas
    -0.57
     invitamos
    -0.57
     himo
    -0.56
    POSITIVE LOGITS
    DockStyle
    1.02
     a
    0.92
    Gimme
    0.81
    CGRectMake
    0.80
    ,:),
    0.77
     an
    0.76
     the
    0.71
    цездатний
    0.67
     EdgeInsets
    0.66
     their
    0.66
    Act Density 0.181%

    No Known Activations