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

    Neuronpedia

    INDEX
    Explanations

    By analyzing the activations, this neuron seems to be looking for mentions of unintended or additional outcomes related to actions or events

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "product" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hornets
    -0.62
    ITED
    -0.62
     Warriors
    -0.61
     Panther
    -0.61
     pup
    -0.61
     mosqu
    -0.60
    ARP
    -0.60
    ©¶æ
    -0.60
     coil
    -0.59
     bee
    -0.58
    POSITIVE LOGITS
    ively
    1.19
    iveness
    1.18
    ivity
    1.16
    ions
    1.03
    ivities
    0.98
    ivist
    0.91
    arian
    0.89
    ivism
    0.88
    urer
    0.84
    itute
    0.81
    Act Density 0.024%

    No Known Activations