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

    Neuronpedia

    INDEX
    Explanations

    pronouns representing people or characters

    oai_token-act-pair · gpt-3.5-turbo

    references to personal experiences or actions involving individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Alright
    -0.71
    tera
    -0.64
    alter
    -0.64
    puff
    -0.64
     Cancel
    -0.63
    cox
    -0.63
    Alright
    -0.62
    legal
    -0.62
    íķ
    -0.62
    âķIJ
    -0.62
    POSITIVE LOGITS
     encountered
    1.51
     noticed
    1.49
     encount
    1.49
     encounter
    1.43
     hear
    1.37
     saw
    1.37
     encounters
    1.35
     spotted
    1.32
     find
    1.32
     encountering
    1.31
    Act Density 0.435%

    No Known Activations