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

    Neuronpedia

    INDEX
    Explanations

    references to varying conditions and contexts in analyses or discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     détach
    -0.57
     nettoyage
    -0.56
    (&:
    -0.56
    GIVEREF
    -0.53
     sauter
    -0.53
     bels
    -0.53
    ModelAttribute
    -0.53
    ApiModelProperty
    -0.53
     ['$
    -0.52
     dépos
    -0.52
    POSITIVE LOGITS
     situations
    1.52
     circumstances
    1.44
     contexts
    1.37
     Situations
    1.25
     scenarios
    1.25
     situation
    1.20
     environments
    1.16
    situation
    1.11
    situ
    1.11
     scenario
    1.10
    Act Density 0.425%

    No Known Activations