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

    Neuronpedia

    INDEX
    Explanations

    words related to obstacles or restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IRECTION
    -0.15
    .toolbox
    -0.15
    ony
    -0.15
    venes
    -0.14
    íĺ¸
    -0.14
     SCO
    -0.13
    bab
    -0.13
    ãģ¹ãģ¦
    -0.13
    appa
    -0.13
    allet
    -0.13
    POSITIVE LOGITS
    /block
    0.19
    peq
    0.16
    -free
    0.15
    -Free
    0.15
    /bar
    0.14
    chief
    0.14
    akhir
    0.14
    ocracy
    0.14
    :block
    0.14
    upakan
    0.14
    Act Density 0.115%

    No Known Activations