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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their associated contextual significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.59
    Naissance
    -0.59
    rd
    -0.56
     imageNamed
    -0.55
    fiez
    -0.55
    intellij
    -0.54
    alyptus
    -0.54
    HasKey
    -0.53
     Lilian
    -0.53
     propios
    -0.53
    POSITIVE LOGITS
    nd
    1.48
    0
    0.86
     thirds
    0.84
    thirds
    0.83
    gether
    0.81
    5
    0.81
     nd
    0.79
    4
    0.79
    ND
    0.77
    nds
    0.76
    Act Density 1.607%

    No Known Activations