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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a comparison or contrasting relationship

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to the existence or presence of certain conditions or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     DEFENSE
    -0.68
    lash
    -0.63
    abases
    -0.62
    Mesh
    -0.58
     Pants
    -0.58
    ockets
    -0.58
    ograms
    -0.58
    emate
    -0.58
     Calling
    -0.57
     RG
    -0.57
    POSITIVE LOGITS
     evidenced
    0.84
     attest
    0.72
     progresses
    0.70
    iHUD
    0.69
     [|
    0.67
    ¥µ
    0.64
     guessed
    0.64
     previously
    0.64
     progressed
    0.63
    pson
    0.63
    Act Density 0.245%

    No Known Activations