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

    Neuronpedia

    INDEX
    Explanations

    phrases or questions that refer to explanations, inquiries, or evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uze
    -0.15
    çĢ
    -0.14
    :uint
    -0.14
    .userInteractionEnabled
    -0.14
     Forrest
    -0.13
    iba
    -0.13
    edx
    -0.13
    ÙĪÙĦÙĪ
    -0.13
     Wealth
    -0.13
     flips
    -0.13
    POSITIVE LOGITS
    spender
    0.17
    villa
    0.16
    pch
    0.16
    ucz
    0.15
     emb
    0.15
    izzy
    0.15
    beg
    0.15
     beg
    0.15
    sth
    0.14
    thinkable
    0.14
    Act Density 0.214%

    No Known Activations