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

    Neuronpedia

    INDEX
    Explanations

    numerical values and time references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    277
    -0.16
    äºĶæľĪ
    -0.14
    ados
    -0.14
    αι
    -0.14
     te
    -0.14
     erg
    -0.14
     Abraham
    -0.14
    ASM
    -0.14
    enos
    -0.13
    lands
    -0.13
    POSITIVE LOGITS
     Alive
    0.16
    .metamodel
    0.15
     alive
    0.15
    ãĥªãĥ¼ãĤº
    0.14
    .hxx
    0.14
    olum
    0.14
    amen
    0.14
    Ø
    0.14
    ORY
    0.14
     пеÑĢепиÑģ
    0.14
    Act Density 0.005%

    No Known Activations