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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "was" and related variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ometimes
    -0.15
    cco
    -0.15
    ãĤ·ãĥ¼
    -0.15
    licit
    -0.15
    eniable
    -0.15
    jmu
    -0.14
    .once
    -0.14
     rarely
    -0.14
    oho
    -0.14
    sometimes
    -0.14
    POSITIVE LOGITS
     during
    0.21
    nt
    0.20
    during
    0.16
    纯
    0.15
     late
    0.15
     During
    0.15
     durante
    0.15
     shortly
    0.15
     larg
    0.14
    During
    0.14
    Act Density 0.079%

    No Known Activations