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

    Neuronpedia

    INDEX
    Explanations

    words associated with disorder and confusion

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ApiModelProperty
    -0.78
    ecore
    -0.76
    JsonPropertyName
    -0.70
    IBarButtonItem
    -0.70
     CanadaChoose
    -0.69
    Tikang
    -0.68
    LookAnd
    -0.67
     Alde
    -0.66
    Халык
    -0.64
    AutoresizingMask
    -0.64
    POSITIVE LOGITS
     mess
    1.27
     messy
    1.25
     chaos
    1.23
     Mess
    1.20
     messes
    1.13
    Mess
    1.12
    Chaos
    1.10
     caos
    1.07
    chaos
    1.05
     Chaos
    1.05
    Act Density 0.035%

    No Known Activations