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

    Neuronpedia

    INDEX
    Explanations

    subjective opinions or personal preferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     restauration
    -0.63
     culturelles
    -0.57
     murale
    -0.55
    uzzy
    -0.54
     provinciale
    -0.52
     citoyens
    -0.52
     químicas
    -0.52
     médicas
    -0.52
    RUnlock
    -0.52
     oprav
    -0.52
    POSITIVE LOGITS
     usually
    1.01
     prefer
    0.97
     prefers
    0.92
     предпочита
    0.91
    Usually
    0.84
    usually
    0.83
     always
    0.81
     preferring
    0.81
     typically
    0.81
    Typically
    0.80
    Act Density 0.261%

    No Known Activations