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

    Neuronpedia

    INDEX
    Explanations

    time-related phrases indicating a future point in time

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express a current or ongoing state

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Died
    -0.64
     Benefits
    -0.61
     Bagg
    -0.59
     Stall
    -0.59
     Berm
    -0.59
     Trafford
    -0.58
     Lisp
    -0.58
     Airl
    -0.58
     Ops
    -0.57
     laughs
    -0.57
    POSITIVE LOGITS
    adays
    1.07
    here
    0.99
    èª
    0.86
    ı
    0.74
     defunct
    0.73
    abouts
    0.69
    nir
    0.69
    ledge
    0.69
    Ùĩ
    0.68
    ivia
    0.67
    Act Density 0.025%

    No Known Activations