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

    Neuronpedia

    INDEX
    Explanations

    phrases related to particular aspects or details of a topic that are worth paying special attention to

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "particularly" indicating a focus on specific details or emphasis in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IDES
    -0.78
    atur
    -0.70
    ves
    -0.69
    hou
    -0.68
    orts
    -0.67
    livion
    -0.67
    uid
    -0.67
    ends
    -0.66
    toggle
    -0.65
    erb
    -0.65
    POSITIVE LOGITS
     evidenced
    0.73
     those
    0.69
     associ
    0.68
     susceptible
    0.67
     targeting
    0.66
     egregious
    0.65
     geared
    0.64
    accompanied
    0.64
     pertaining
    0.63
     advantageous
    0.63
    Act Density 0.036%

    No Known Activations