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

    Neuronpedia

    INDEX
    Explanations

    phrases and words indicating collaboration or partnership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulu
    -0.15
    idon
    -0.15
    front
    -0.15
    enger
    -0.15
    elan
    -0.15
    shore
    -0.15
    undo
    -0.15
    å®ľ
    -0.15
    .Override
    -0.14
    iza
    -0.14
    POSITIVE LOGITS
     themselves
    0.18
     TF
    0.17
    viso
    0.17
    avn
    0.16
     tf
    0.15
     exclusively
    0.15
    pire
    0.15
     siÄĻ
    0.15
     forces
    0.14
     mình
    0.14
    Act Density 0.095%

    No Known Activations