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

    Neuronpedia

    INDEX
    Explanations

    interactions involving conflict and resolution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BufferException
    -0.72
    RegistryLite
    -0.70
    ArgsConstructor
    -0.66
     estekak
    -0.64
    rungsseite
    -0.60
    addContainerGap
    -0.56
    idem
    -0.55
    marginVertical
    -0.54
     дописавши
    -0.54
    ActionResult
    -0.54
    POSITIVE LOGITS
     teasing
    0.99
     tease
    0.93
     teased
    0.91
     taunt
    0.84
     scold
    0.77
     scolded
    0.76
    encouragement
    0.74
     encouragement
    0.72
     reproach
    0.71
     coax
    0.70
    Act Density 0.467%

    No Known Activations