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

    Neuronpedia

    INDEX
    Explanations

    attributes associated with reliability and frequency in various contexts

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

    manner or frequency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .*")]
    -0.72
     ब्रेकडाउन
    -0.71
     Verſ
    -0.71
    OrNil
    -0.69
     myſelf
    -0.68
    rungsseite
    -0.66
    DrawerToggle
    -0.66
     Autorizaciones
    -0.65
    WithIOException
    -0.65
    ApiModelProperty
    -0.64
    POSITIVE LOGITS
     manner
    0.38
     way
    0.32
     time
    0.31
     context
    0.29
     circonstances
    0.29
     mode
    0.28
     Lake
    0.27
    .
    0.27
     scientific
    0.27
     point
    0.27
    Act Density 0.107%

    No Known Activations