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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating significant medical or health-related causes and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ack
    -0.19
     Bones
    -0.16
     Hollow
    -0.15
    aju
    -0.15
     Pret
    -0.15
     Agu
    -0.15
     marshal
    -0.14
    bone
    -0.14
     Bone
    -0.14
    ique
    -0.14
    POSITIVE LOGITS
    ungle
    0.18
    ichick
    0.17
    plr
    0.16
    Äįit
    0.16
    اÙĨس
    0.16
    vens
    0.15
    olum
    0.15
     Pou
    0.14
    yne
    0.14
    reater
    0.14
    Act Density 0.001%

    No Known Activations