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

    Neuronpedia

    INDEX
    Explanations

    questions and statements that seek clarification or confirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stood
    -0.16
    ils
    -0.15
    Active
    -0.15
    gether
    -0.15
    ilst
    -0.14
    å§
    -0.14
    erdings
    -0.14
    ics
    -0.14
    icked
    -0.14
    hiro
    -0.14
    POSITIVE LOGITS
    abella
    0.14
    WSC
    0.14
    vir
    0.14
    olen
    0.14
    олÑİ
    0.14
    iping
    0.14
    aines
    0.13
    hur
    0.13
    uard
    0.13
    ambi
    0.13
    Act Density 0.117%

    No Known Activations