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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating potential consequences or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ior
    -0.17
    aura
    -0.16
    nton
    -0.16
    ito
    -0.16
    Touchable
    -0.16
    inton
    -0.15
    ìķħ
    -0.15
    ãģĨãģ¡
    -0.14
    vable
    -0.14
    elling
    -0.14
    POSITIVE LOGITS
     grounds
    0.17
    ASN
    0.16
    éĻµ
    0.15
    cken
    0.15
     helpful
    0.14
    apers
    0.14
    odal
    0.14
     interpreted
    0.14
    enos
    0.14
    è¾°
    0.14
    Act Density 0.296%

    No Known Activations