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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "ban" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <unused68>
    -0.98
    <unused52>
    -0.97
    <unused79>
    -0.97
     betweenstory
    -0.97
    <unused14>
    -0.97
    [@BOS@]
    -0.97
    <unused41>
    -0.96
    <unused8>
    -0.96
    <unused3>
    -0.96
    <unused16>
    -0.96
    POSITIVE LOGITS
     arm
    0.68
     ban
    0.66
     AS
    0.58
    arm
    0.58
    ban
    0.56
    AS
    0.55
     e
    0.54
    Ban
    0.53
     
    0.51
     Ban
    0.50
    Act Density 0.492%

    No Known Activations