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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with an arrow symbol

    oai_token-act-pair · gpt-3.5-turbo

    instances of a particular special character or sequence that appears multiple times in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiActiveUnfocused
    -0.78
     Morse
    -0.69
     CLR
    -0.68
     lethal
    -0.65
     scattering
    -0.63
     afore
    -0.63
     gib
    -0.63
     treadmill
    -0.63
     shack
    -0.62
     Townsend
    -0.60
    POSITIVE LOGITS
    º
    0.95
    ¹
    0.87
    £
    0.87
    agree
    0.85
    ¬
    0.85
    ı
    0.84
    į
    0.84
    gat
    0.81
    ¤
    0.80
    ask
    0.80
    Act Density 0.171%

    No Known Activations