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

    Neuronpedia

    INDEX
    Explanations

    social activities, trends, and behaviors that people are engaging in or discussing

    oai_token-act-pair · gpt-3.5-turbo

    various forms of the verb "to be" and its usage in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     predecessor
    -0.91
     srfAttach
    -0.81
    ModLoader
    -0.76
     Rhodes
    -0.74
    ãĥ¯
    -0.73
    è£ħ
    -0.72
    Ü
    -0.70
    ernaut
    -0.67
    ãĥķãĤ©
    -0.65
     Rug
    -0.65
    POSITIVE LOGITS
     clam
    0.99
     grav
    0.86
     misunderstand
    0.82
     starving
    0.80
     underest
    0.78
     noticing
    0.78
     misinterpret
    0.77
     everywhere
    0.75
     dying
    0.75
     misconception
    0.74
    Act Density 0.245%

    No Known Activations