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

    Neuronpedia

    INDEX
    Explanations

    phrases or statements where something specific can be said about a subject or situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases relating to the existence or actions of people and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IVERS
    -0.67
     jeans
    -0.66
    ãĥŁ
    -0.64
    ĺ
    -0.64
     Formation
    -0.63
     Screen
    -0.63
     Âł Âł
    -0.62
     Savings
    -0.62
     Sources
    -0.61
    NAS
    -0.60
    POSITIVE LOGITS
    ortium
    0.75
    paralle
    0.71
     satisfies
    0.69
    rament
    0.66
    anooga
    0.66
    nants
    0.66
     overlap
    0.65
     registers
    0.65
    avorite
    0.64
     parallels
    0.63
    Act Density 0.156%

    No Known Activations