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

    Neuronpedia

    INDEX
    Explanations

    references to societal norms and expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    annel
    -0.17
    immer
    -0.15
    allel
    -0.15
    igham
    -0.15
    vard
    -0.15
    undry
    -0.15
    CSI
    -0.14
    AsyncResult
    -0.14
    esor
    -0.14
    ovel
    -0.14
    POSITIVE LOGITS
     Rodrig
    0.17
    ernaut
    0.16
    ropoda
    0.15
    .mk
    0.14
    ible
    0.14
     ev
    0.14
     ROM
    0.14
     topo
    0.14
    cha
    0.13
     Wind
    0.13
    Act Density 0.245%

    No Known Activations