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

    Neuronpedia

    INDEX
    Explanations

    phrases associated with perceptions or evaluations of experiences or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     varones
    -0.55
    ientôt
    -0.53
    harusnya
    -0.52
     cuentos
    -0.52
     aikaa
    -0.49
     bileklik
    -0.49
     mulighed
    -0.49
     tutkim
    -0.48
    tidaknya
    -0.47
    Identyfik
    -0.47
    POSITIVE LOGITS
     Ah
    0.71
     impression
    0.70
     Aw
    0.65
    impression
    0.65
    Ah
    0.64
     Impression
    0.59
    Impression
    0.56
    Aw
    0.56
     away
    0.55
     Away
    0.54
    Act Density 0.222%

    No Known Activations