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

    Neuronpedia

    INDEX
    Explanations

    terms related to consequences, values, and abstract concepts

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to political and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arnaev
    -0.56
    anwhile
    -0.55
    owicz
    -0.54
     Mub
    -0.50
    ersen
    -0.50
    Downloadha
    -0.50
    ewski
    -0.49
    etsk
    -0.48
    zl
    -0.47
     Shed
    -0.47
    POSITIVE LOGITS
    votes
    0.54
    ravity
    0.50
    thood
    0.48
    lessness
    0.46
     relating
    0.45
     proportions
    0.44
     stature
    0.42
    advertising
    0.42
    Reviewer
    0.42
     fame
    0.42
    Act Density 1.249%

    No Known Activations