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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and specific geographic or cultural references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EIF
    -0.17
    orphic
    -0.17
    бом
    -0.16
    hol
    -0.16
    holm
    -0.15
    oucher
    -0.15
    DST
    -0.15
    NSS
    -0.14
    deo
    -0.14
    cratch
    -0.14
    POSITIVE LOGITS
    izu
    0.17
    ros
    0.16
    roy
    0.15
    ogie
    0.15
     Mont
    0.15
    VERS
    0.15
    -g
    0.14
    ode
    0.14
    trs
    0.14
     macro
    0.14
    Act Density 0.029%

    No Known Activations