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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific actions or events

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to various significant events and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     educated
    -0.54
    algia
    -0.52
    okin
    -0.49
    ropolitan
    -0.49
     consolation
    -0.48
     businessmen
    -0.47
    oln
    -0.47
    itialized
    -0.46
    uable
    -0.46
     coincidence
    -0.46
    POSITIVE LOGITS
    .''
    0.70
    .''.
    0.69
    .�
    0.69
    .
    0.68
    .[
    0.66
    .}
    0.65
    .</
    0.63
    ."
    0.62
    .<
    0.62
    .'
    0.60
    Act Density 1.206%

    No Known Activations