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

    Neuronpedia

    INDEX
    Explanations

    phrases that express skepticism or critical analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kå
    -0.14
    ANTE
    -0.14
    ocab
    -0.14
    éru
    -0.14
    åŀ
    -0.14
    ueva
    -0.13
    ieber
    -0.13
    ussen
    -0.13
    ante
    -0.13
    bab
    -0.13
    POSITIVE LOGITS
     deeper
    0.50
     deep
    0.44
    æ·±
    0.40
     digging
    0.40
     depth
    0.39
     dig
    0.39
    deep
    0.37
    Dig
    0.37
     Dig
    0.36
    dig
    0.35
    Act Density 0.265%

    No Known Activations