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

    Neuronpedia

    INDEX
    Explanations

    words related to critical or important aspects of a situation

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with prediction, assessment, and evaluation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     loves
    -0.69
     believes
    -0.67
     hopes
    -0.64
     regrets
    -0.64
    laughs
    -0.64
     argues
    -0.60
    ãĥ³ãĤ¸
    -0.60
    Adds
    -0.59
     likes
    -0.59
    OV
    -0.59
    POSITIVE LOGITS
     are
    1.36
     were
    1.35
     expire
    1.34
     arise
    1.28
     occur
    1.26
     exist
    1.24
     collide
    1.20
     aren
    1.19
    were
    1.17
     weren
    1.17
    Act Density 0.308%

    No Known Activations