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

    Neuronpedia

    INDEX
    Explanations

    phrases related to trust, proof, and verification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyTitle
    -0.57
    tiness
    -0.55
    abestanden
    -0.54
    componentWill
    -0.48
    äť
    -0.46
    jLabel
    -0.46
    resaid
    -0.45
    __(/*!
    -0.43
    setViewName
    -0.42
     Rejo
    -0.41
    POSITIVE LOGITS
     done
    0.89
     Done
    0.75
     DONE
    0.72
    done
    0.71
    WireFormatLite
    0.71
     propOrder
    0.70
    Doing
    0.66
     ചെയ
    0.65
    し
    0.65
    doing
    0.65
    Act Density 0.054%

    No Known Activations