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

    Neuronpedia

    INDEX
    Explanations

    references to intimacy and closeness in relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WireFormatLite
    -0.87
    QMetaType
    -0.86
    IsMutable
    -0.85
    ModelAdmin
    -0.83
     Brandt
    -0.79
     Wilk
    -0.77
     Steinberg
    -0.77
    ModelForm
    -0.76
    ीय
    -0.76
     urm
    -0.75
    POSITIVE LOGITS
     close
    1.70
     Close
    1.66
     CLOSE
    1.59
    CLOSE
    1.56
    close
    1.52
    Close
    1.51
     Closer
    1.34
     Clos
    1.32
     closer
    1.30
     CLOS
    1.30
    Act Density 0.058%

    No Known Activations