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

    Neuronpedia

    INDEX
    Explanations

    personal anecdotes or stories

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal experiences and emotions related to family and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    haar
    -0.64
    issance
    -0.59
     Dhabi
    -0.55
    pires
    -0.52
    uid
    -0.51
    bris
    -0.51
    ettel
    -0.51
    rium
    -0.51
    ngth
    -0.50
    oshenko
    -0.50
    POSITIVE LOGITS
    their
    1.61
    Their
    1.49
    they
    1.49
     my
    1.44
     myself
    1.44
    They
    1.41
     Their
    1.40
     they
    1.40
     They
    1.39
     THEIR
    1.39
    Act Density 0.775%

    No Known Activations