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

    Neuronpedia

    INDEX
    Explanations

    phrases related to growth or development over time

    oai_token-act-pair · gpt-3.5-turbo

    references to change and development over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Assembly
    -0.73
    olicited
    -0.72
    avering
    -0.70
    abel
    -0.70
    ãĥīãĥ©
    -0.69
     Roads
    -0.67
    zzi
    -0.66
    oka
    -0.65
     Mub
    -0.65
    mir
    -0.64
    POSITIVE LOGITS
    iator
    0.77
    anwhile
    0.75
     evolve
    0.74
     exponentially
    0.74
    arily
    0.71
     into
    0.70
     accordingly
    0.69
     stale
    0.66
     behavi
    0.66
    etically
    0.65
    Act Density 0.030%

    No Known Activations