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

    Neuronpedia

    INDEX
    Explanations

    words related to measuring and comparing quantities or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     finalist
    -0.15
     trust
    -0.14
    太éĥİ
    -0.14
    LOSS
    -0.14
     anywhere
    -0.14
     neither
    -0.13
     finalists
    -0.13
    rish
    -0.13
    èĽĽ
    -0.13
    trust
    -0.13
    POSITIVE LOGITS
     inactive
    0.29
     reserved
    0.25
    Inactive
    0.25
     reserve
    0.24
    inactive
    0.24
     reserva
    0.23
     quiet
    0.23
    reserved
    0.22
     reserves
    0.21
    _reserved
    0.20
    Act Density 0.021%

    No Known Activations