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

    Neuronpedia

    INDEX
    Explanations

    phrases related to entering a specific state or action

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "goes into."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fortunately
    -0.69
    onica
    -0.66
    selves
    -0.64
    æĿ
    -0.62
    tch
    -0.62
    Roy
    -0.62
    Bey
    -0.62
    ilege
    -0.61
     travelled
    -0.60
    bane
    -0.59
    POSITIVE LOGITS
     hiber
    1.06
     hiding
    1.03
     cardiac
    0.92
     exile
    0.92
     meltdown
    0.90
     lockdown
    0.85
     remission
    0.85
     detail
    0.84
     unch
    0.83
     battle
    0.80
    Act Density 0.077%

    No Known Activations