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

    Neuronpedia

    INDEX
    Explanations

    phrases or terms related to growth or escalation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating growth or escalation of various issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ayer
    -0.84
    chery
    -0.83
     Mub
    -0.83
    notice
    -0.80
    ère
    -0.79
    zed
    -0.77
    udo
    -0.77
    PLIED
    -0.77
    claimer
    -0.77
    iqu
    -0.76
    POSITIVE LOGITS
     tides
    0.89
     tide
    0.85
     tendency
    0.84
     temperatures
    0.82
     flux
    0.82
     trends
    0.81
     fortunes
    0.81
     trend
    0.79
     incidence
    0.77
     technologies
    0.77
    Act Density 0.081%

    No Known Activations