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

    Neuronpedia

    INDEX
    Explanations

    references to joint initiatives or partnerships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    spannung
    -0.36
     stuk
    -0.36
    isesti
    -0.36
    ścioła
    -0.35
    $)$
    -0.35
     Gucci
    -0.34
    versorgung
    -0.34
    وردار
    -0.34
    sula
    -0.34
     caras
    -0.34
    POSITIVE LOGITS
     Joint
    1.18
     JOINT
    1.07
     joint
    1.05
     Joints
    1.02
    Joint
    1.01
    joint
    0.97
     joints
    0.96
    JOINT
    0.90
     Join
    0.86
    joints
    0.82
    Act Density 0.250%

    No Known Activations