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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate hierarchical or sequential directives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uf
    -0.16
    rak
    -0.14
    illa
    -0.14
    us
    -0.14
    ish
    -0.14
    ka
    -0.14
    ise
    -0.13
    ahkan
    -0.13
    rack
    -0.13
    olutely
    -0.13
    POSITIVE LOGITS
    annes
    0.15
    ÑģÑĮ
    0.14
    yz
    0.14
    Assignable
    0.14
     latter
    0.14
    OMATIC
    0.14
    ynet
    0.14
    oth
    0.14
    ittings
    0.14
    Ñĩем
    0.14
    Act Density 0.044%

    No Known Activations