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

    Neuronpedia

    INDEX
    Explanations

    phrases related to future projections and growth

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to future projections and trends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ossip
    -0.73
    assin
    -0.71
    checked
    -0.68
    talking
    -0.61
    hearted
    -0.59
     Pupp
    -0.59
     Sung
    -0.59
    thing
    -0.59
    aying
    -0.58
    assi
    -0.58
    POSITIVE LOGITS
     overtake
    1.16
     exceed
    1.16
     accelerate
    1.13
     soar
    1.13
     increase
    1.11
     remain
    1.10
     continue
    1.09
     surpass
    1.06
     reduce
    1.05
     become
    1.04
    Act Density 0.215%

    No Known Activations