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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate frequency or repetition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vala
    -0.16
    zych
    -0.15
    omor
    -0.15
    EFAULT
    -0.15
    ioxide
    -0.14
    ropa
    -0.14
    rief
    -0.14
    üt
    -0.14
    елик
    -0.14
     HID
    -0.14
    POSITIVE LOGITS
     so
    0.22
     blue
    0.22
     Blue
    0.21
     once
    0.21
     now
    0.19
    /blue
    0.18
     tanto
    0.18
    Blue
    0.17
     oc
    0.17
     Mann
    0.17
    Act Density 0.022%

    No Known Activations