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

    Neuronpedia

    INDEX
    Explanations

    phrases related to hypothetical or conditional scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    textAlignment
    -0.55
     Majefty
    -0.51
     Cæsar
    -0.50
    щаются
    -0.49
     faſt
    -0.49
     pleaſure
    -0.48
    Referințe
    -0.47
     themſelves
    -0.47
     ſhall
    -0.47
     cauſe
    -0.46
    POSITIVE LOGITS
     للمعارف
    0.80
     صوتيه
    0.75
     hubiera
    0.74
    tagHelperRunner
    0.74
    would
    0.73
     would
    0.72
     WOULD
    0.69
     gdyby
    0.67
    Would
    0.67
    RegistryLite
    0.66
    Act Density 0.331%

    No Known Activations