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

    Neuronpedia

    INDEX
    Explanations

    references to negative qualities or poor conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GOTREF
    -0.66
    sprü
    -0.63
     gynhyrchwyd
    -0.61
     flèche
    -0.61
    ]='\
    -0.60
     nødven
    -0.59
    lidene
    -0.59
     up
    -0.59
     uninterrupted
    -0.58
    centerline
    -0.58
    POSITIVE LOGITS
     POOR
    0.80
    poor
    0.76
     Poor
    0.71
     poor
    0.71
     poorer
    0.71
    Poor
    0.68
    弱
    0.67
     Weak
    0.64
     poorly
    0.64
     inadequate
    0.64
    Act Density 0.507%

    No Known Activations