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

    Neuronpedia

    INDEX
    Explanations

    concepts related to openness and understanding in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    openness, diversity, or broadening perspectives

    np_acts-logits-general · gemini-2.0-flash

    opening up perspectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hdys
    -0.44
     Private
    -0.44
    cdnjs
    -0.42
    interceptors
    -0.41
     private
    -0.41
    private
    -0.40
     finalised
    -0.40
    gor
    -0.39
     precise
    -0.39
     evid
    -0.39
    POSITIVE LOGITS
     broadening
    1.01
     broaden
    0.94
    diversity
    0.84
     horizons
    0.82
     broadened
    0.81
     perspectives
    0.80
     widen
    0.80
     diversity
    0.80
    AnchorStyles
    0.79
     saites
    0.78
    Act Density 0.234%

    No Known Activations