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

    Neuronpedia

    INDEX
    Explanations

    use of first-person pronouns and phrases indicating speaker involvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     OTHERWISE
    -0.65
    addContainerGap
    -0.64
     mapStateToProps
    -0.60
    extAlignment
    -0.60
     thereupon
    -0.60
    DEPORTES
    -0.59
    ſelf
    -0.59
     Diſ
    -0.59
    UVWXYZ
    -0.58
    apunov
    -0.58
    POSITIVE LOGITS
     autorytatywna
    0.81
    Erreferentziak
    0.59
    וויק
    0.58
    RegistryLite
    0.57
    protoimpl
    0.56
    WithEmail
    0.56
    ScreenState
    0.52
    Източници
    0.51
    rungsseite
    0.50
    횟
    0.50
    Act Density 0.564%

    No Known Activations