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

    Neuronpedia

    INDEX
    Explanations

    terms related to loyalty and support

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ThemeOverlay
    -0.83
     &___
    -0.81
     AssemblyCulture
    -0.75
    AFX
    -0.74
    ArgsConstructor
    -0.74
     متعلقه
    -0.74
    }")]
    -0.73
    ItemBackground
    -0.72
     <=",
    -0.71
    verwijspagina
    -0.70
    POSITIVE LOGITS
     toward
    0.54
     to
    0.53
    ไป
    0.51
     blanches
    0.50
     recenti
    0.50
     for
    0.48
     dedicato
    0.48
     towards
    0.47
     recours
    0.47
     into
    0.47
    Act Density 0.428%

    No Known Activations