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

    Neuronpedia

    INDEX
    Explanations

    references to police

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    afia
    -0.16
    lisi
    -0.15
    çĥ
    -0.15
    IDI
    -0.15
     subs
    -0.15
     vitae
    -0.15
    lej
    -0.15
    ¹Ħ
    -0.14
    .getDocument
    -0.14
    uki
    -0.13
    POSITIVE LOGITS
    ppo
    0.16
    andle
    0.15
     randomness
    0.14
    prit
    0.14
     corr
    0.14
    going
    0.14
     excess
    0.14
    ighter
    0.13
    earer
    0.13
    go
    0.13
    Act Density 0.021%

    No Known Activations