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

    Neuronpedia

    INDEX
    Explanations

    requests for feedback and interaction from the audience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .bz
    -0.17
    jango
    -0.16
     hol
    -0.15
    amus
    -0.15
    omb
    -0.15
    alle
    -0.15
    917
    -0.14
    avana
    -0.14
    ayan
    -0.14
    pollo
    -0.14
    POSITIVE LOGITS
    itos
    0.17
    ê¶ģ
    0.16
    TEE
    0.14
     Hindered
    0.14
    ellas
    0.14
    ừng
    0.14
    dac
    0.13
    ercul
    0.13
    ienes
    0.13
    acers
    0.13
    Act Density 0.035%

    No Known Activations