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

    Neuronpedia

    INDEX
    Explanations

    phrases related to computer programming and technology

    oai_token-act-pair · gpt-3.5-turbo

    specific terms related to technology and innovation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AGES
    -0.91
    ola
    -0.91
    onia
    -0.81
    ón
    -0.81
    oes
    -0.80
    atoes
    -0.80
    rencies
    -0.77
    onica
    -0.76
     CITY
    -0.76
    asaki
    -0.75
    POSITIVE LOGITS
     Im
    0.94
     Rez
    0.88
     im
    0.86
     Impro
    0.84
     Inter
    0.80
     Shap
    0.76
     Inf
    0.75
     Neg
    0.74
     simul
    0.73
     Ir
    0.72
    Act Density 0.294%

    No Known Activations