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

    Neuronpedia

    INDEX
    Explanations

    phrases related to governmental or political actions

    oai_token-act-pair · gpt-3.5-turbo

    components or elements that signify uncertainty or ambiguity in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    —"
    -0.55
     Ethernet
    -0.55
    enger
    -0.54
    iste
    -0.54
     Brewery
    -0.54
     DevOnline
    -0.53
     IPA
    -0.53
     café
    -0.51
    estones
    -0.50
     naming
    -0.50
    POSITIVE LOGITS
    widget
    0.59
    maxwell
    0.58
    etheless
    0.57
    ↵Âł
    0.56
     grate
    0.56
    consider
    0.54
    ↵↵
    0.53
     dont
    0.52
     david
    0.52
    ãħĭãħĭ
    0.52
    Act Density 0.972%

    No Known Activations