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

    Neuronpedia

    INDEX
    Explanations

    phrases related to freedom and liberation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "freed" and its variations related to release or liberation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iop
    -0.61
     bacter
    -0.60
     spat
    -0.60
     iod
    -0.59
     omission
    -0.58
     fluor
    -0.57
     Humph
    -0.57
    ibur
    -0.56
     Grimm
    -0.56
    soDeliveryDate
    -0.55
    POSITIVE LOGITS
    bies
    1.04
    ktop
    1.02
    irs
    0.94
     freeing
    0.88
    egu
    0.84
     freed
    0.82
    ntil
    0.81
    bie
    0.81
    anding
    0.80
     slaves
    0.80
    Act Density 0.025%

    No Known Activations