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

    Neuronpedia

    INDEX
    Explanations

    references to interpersonal challenges and difficulties in relationships, particularly in a workplace context

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

    dealing with annoyances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.37
     peuples
    -0.33
     huellas
    -0.32
    tagHelperRunner
    -0.32
    getValues
    -0.32
     récentes
    -0.32
     ecológico
    -0.32
     officielles
    -0.31
     ProtoMessage
    -0.31
     técnicas
    -0.31
    POSITIVE LOGITS
     annoying
    0.69
     obnoxious
    0.64
     irritating
    0.63
    ContentLoaded
    0.60
     insu
    0.57
     annoy
    0.56
     annoyance
    0.56
     nuisance
    0.56
     nuis
    0.53
    TintMode
    0.52
    Act Density 0.186%

    No Known Activations