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

    Neuronpedia

    INDEX
    Explanations

    the word "Things" at the start of a sentence

    oai_token-act-pair · gpt-3.5-turbo

    the word "things" and its variations, indicating discussions about events or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iary
    -0.92
    pless
    -0.75
    iaries
    -0.72
    bern
    -0.71
    asio
    -0.69
     Flavoring
    -0.69
    resents
    -0.68
    gee
    -0.66
    lication
    -0.63
    ardi
    -0.63
    POSITIVE LOGITS
     transpired
    1.01
     happen
    0.98
     happened
    0.97
     happening
    0.88
     unfolded
    0.87
     unfold
    0.86
     escalated
    0.86
     pertaining
    0.83
     escalate
    0.80
     happ
    0.79
    Act Density 0.044%

    No Known Activations