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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "er" followed by a word beginning with a lowercase letter

    oai_token-act-pair · gpt-3.5-turbo

    words related to address or reference, particularly in contexts involving characters or entities in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yip
    -0.80
    thood
    -0.70
     Mub
    -0.70
    jri
    -0.69
     Flavoring
    -0.69
    ccoli
    -0.68
     innocence
    -0.68
    okemon
    -0.66
     nationally
    -0.66
     hover
    -0.65
    POSITIVE LOGITS
    ipel
    1.00
    abeth
    0.82
    onomic
    0.76
    lich
    0.75
    404
    0.74
    ée
    0.73
    ENE
    0.73
    ¯
    0.70
    schild
    0.69
    meyer
    0.69
    Act Density 0.090%

    No Known Activations