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

    Neuronpedia

    INDEX
    Explanations

    phrases indicative of significant financial investments or revenue generation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eux
    -0.17
    ë¹Ļ
    -0.14
    ká
    -0.14
    marshal
    -0.14
     THEM
    -0.14
     ragaz
    -0.14
    Verts
    -0.13
    виÑĤ
    -0.13
    hoa
    -0.13
    ç»ĻæĪij
    -0.13
    POSITIVE LOGITS
     there
    0.32
     ÙģØ¥ÙĨ
    0.27
     we
    0.27
     it
    0.27
    there
    0.25
     they
    0.23
     nothing
    0.20
     thì
    0.20
    we
    0.20
    they
    0.19
    Act Density 0.474%

    No Known Activations