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

    Neuronpedia

    INDEX
    Explanations

    phrases related to complaints or objections

    oai_token-act-pair · gpt-3.5-turbo

    references to conspiracy theories or questionable claims about individuals or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nces
    -0.86
    lasses
    -0.76
    xual
    -0.75
    rals
    -0.71
     Mines
    -0.68
    itals
    -0.67
    ney
    -0.66
     Morgan
    -0.65
    nings
    -0.64
    vest
    -0.64
    POSITIVE LOGITS
    lication
    0.73
    -+-+-+-+
    0.73
    cloth
    0.71
    isbury
    0.69
     outgoing
    0.68
     beginnings
    0.66
    entimes
    0.66
    aho
    0.65
    osal
    0.65
    endi
    0.64
    Act Density 0.030%

    No Known Activations