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

    Neuronpedia

    INDEX
    Explanations

    phrases related to adjustable objects or equipment

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to physical mechanics and properties of materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    league
    -0.64
    76561
    -0.60
    ticket
    -0.58
    ç«
    -0.56
     playbook
    -0.56
    artisan
    -0.56
     Inquisition
    -0.55
    government
    -0.55
    vernment
    -0.55
    berman
    -0.54
    POSITIVE LOGITS
     electrons
    0.77
     gradient
    0.73
     velocity
    0.71
     atoms
    0.69
     geometry
    0.68
     diameter
    0.67
     intervals
    0.64
    ynamic
    0.64
     pixels
    0.63
     particles
    0.63
    Act Density 0.843%

    No Known Activations