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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal defense and defensive actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     subject
    -0.52
    tagHelperRunner
    -0.50
    ApiModelProperty
    -0.45
    Subject
    -0.45
     affection
    -0.44
    scribers
    -0.44
    MessageTagHelper
    -0.43
     impression
    -0.42
     character
    -0.41
     contrasted
    -0.40
    POSITIVE LOGITS
     defence
    0.79
     defense
    0.77
    defense
    0.74
    defence
    0.72
     defensa
    0.58
     defences
    0.57
    utilisons
    0.57
     defenses
    0.56
    Defense
    0.56
    Defence
    0.56
    Act Density 0.415%

    No Known Activations