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

    Neuronpedia

    INDEX
    Explanations

    references to care services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ³
    -2.43
    Ļª
    -2.43
    ĨĴ
    -2.38
    ¯
    -2.34
    £
    -2.18
    ı
    -2.09
    ¾
    -2.06
    ĵ
    -2.02
    §
    -1.98
    ĥ½
    -1.95
    POSITIVE LOGITS
    thouse
    1.89
    gens
    1.59
     leaks
    1.53
    azzo
    1.50
    fully
    1.49
     Instr
    1.44
    uable
    1.42
    gate
    1.39
    jax
    1.39
     leaked
    1.39
    Act Density 0.007%

    No Known Activations