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

    Neuronpedia

    INDEX
    Explanations

    comparisons using the structure "as [adjective] as"

    oai_token-act-pair · gpt-3.5-turbo

    comparisons using the phrase "as [adjective] as."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ASED
    -0.63
     Picks
    -0.63
    ASE
    -0.63
     Versus
    -0.60
     Hast
    -0.60
    WAYS
    -0.60
     Flavoring
    -0.59
    rises
    -0.58
     Limits
    -0.55
    Leaks
    -0.55
    POSITIVE LOGITS
    pired
    1.21
    ym
    1.07
    phy
    1.04
     follows
    1.02
    pires
    1.01
    ynchron
    0.96
    phalt
    0.95
    ocial
    0.92
     close
    0.88
     far
    0.86
    Act Density 0.051%

    No Known Activations