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

    Neuronpedia

    INDEX
    Explanations

    instances of annoyance or frustration related to social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SqlClient
    -0.60
     Coup
    -0.55
    UMBIA
    -0.54
     rangka
    -0.53
    RUnlock
    -0.52
     Bound
    -0.49
     vững
    -0.48
    QUAL
    -0.47
    kapet
    -0.47
     cDNA
    -0.47
    POSITIVE LOGITS
     nagging
    1.15
     annoying
    1.14
     nuisance
    1.12
     harassing
    0.99
     irritating
    0.96
     annoy
    0.95
     harassment
    0.95
     harass
    0.93
     persistent
    0.92
     persistently
    0.89
    Act Density 0.244%

    No Known Activations