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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to personal history and identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raya
    -0.19
    chine
    -0.15
    INET
    -0.15
    .boost
    -0.15
    ĥ
    -0.14
    ucher
    -0.14
    dera
    -0.14
    assin
    -0.14
    hoo
    -0.14
    æģ¯
    -0.13
    POSITIVE LOGITS
     forgot
    0.16
     spec
    0.15
    enger
    0.15
    forgot
    0.15
    ामन
    0.15
     cap
    0.14
     Know
    0.14
    {{
    0.14
    osh
    0.13
     simp
    0.13
    Act Density 0.007%

    No Known Activations