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

    Neuronpedia

    INDEX
    Explanations

    common verbs followed by descriptions of physical actions

    oai_token-act-pair · gpt-3.5-turbo

    punctuation, specifically commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UF
    -0.74
    cin
    -0.71
    iq
    -0.66
    uffer
    -0.66
    tnc
    -0.66
    enary
    -0.66
    orn
    -0.64
    eus
    -0.64
    chell
    -0.63
     guiActiveUnfocused
    -0.63
    POSITIVE LOGITS
     huh
    1.03
     albeit
    1.02
     insofar
    0.99
     however
    0.96
     though
    0.92
     sir
    0.89
     but
    0.87
     yes
    0.82
     although
    0.82
     eh
    0.81
    Act Density 0.489%

    No Known Activations