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

    Neuronpedia

    INDEX
    Explanations

    phrases related to directing attention or focus

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to directing attention and focus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Slip
    -0.71
     Signed
    -0.68
     sworn
    -0.68
     photoc
    -0.68
     Incredible
    -0.64
     signed
    -0.64
     Wish
    -0.64
     Chains
    -0.62
     Amen
    -0.62
    signed
    -0.60
    POSITIVE LOGITS
     squarely
    0.98
    izons
    0.89
     toward
    0.89
    phasis
    0.88
     foc
    0.85
     attention
    0.85
     focused
    0.84
     elsewhere
    0.83
    vre
    0.83
    ocusing
    0.82
    Act Density 0.206%

    No Known Activations