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

    Neuronpedia

    INDEX
    Explanations

    phrases or statements presented by a specific person

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual in a context of discussion or reporting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reach
    -0.76
    noon
    -0.74
    anking
    -0.68
    iries
    -0.66
    Interested
    -0.65
    rocket
    -0.63
    Lim
    -0.63
    earch
    -0.63
    requisite
    -0.60
     expiration
    -0.58
    POSITIVE LOGITS
    'd
    1.06
    'll
    0.94
     said
    0.87
    aeus
    0.86
     wrote
    0.84
     tweeted
    0.82
    said
    0.78
     says
    0.76
     joked
    0.76
     lamented
    0.73
    Act Density 0.079%

    No Known Activations