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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating recognition or reputation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ars
    -0.17
    dk
    -0.14
    ors
    -0.14
    incer
    -0.14
    imens
    -0.14
    dda
    -0.14
    éĥİ
    -0.14
    NST
    -0.14
    istol
    -0.14
    ulation
    -0.14
    POSITIVE LOGITS
    rops
    0.15
    CAC
    0.15
    PUTE
    0.15
    ledge
    0.15
    s
    0.15
    enze
    0.14
    ÑģÑĮ
    0.14
    923
    0.14
    ienie
    0.14
    ril
    0.14
    Act Density 0.040%

    No Known Activations