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

    Neuronpedia

    INDEX
    Explanations

    phrases related to progressive movement or gradual development

    oai_token-act-pair · gpt-3.5-turbo

    references to winding paths or roads

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.73
    Ĥİ
    -0.69
    Ħ¢
    -0.67
    ordan
    -0.67
    eele
    -0.64
    reme
    -0.64
    ORE
    -0.64
    rity
    -0.61
    essors
    -0.61
     IMAGES
    -0.61
    POSITIVE LOGITS
     winding
    1.27
    ewater
    0.89
    ãĤ¤ãĥĪ
    0.82
    bum
    0.80
    lass
    0.77
    stead
    0.77
    tenance
    0.74
    glers
    0.74
     conduc
    0.73
     therap
    0.71
    Act Density 0.009%

    No Known Activations