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

    Neuronpedia

    INDEX
    Explanations

    verbs related to desires or intentions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating desires or intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    à¼
    -0.78
    ulty
    -0.73
    è¦ļéĨĴ
    -0.72
    mson
    -0.71
    ilion
    -0.71
    rome
    -0.69
    miah
    -0.69
    illian
    -0.69
    igmatic
    -0.66
    nants
    -0.65
    POSITIVE LOGITS
     to
    1.15
     assurances
    0.94
     us
    0.91
     nothing
    0.85
    reprene
    0.84
     rid
    0.82
     clarification
    0.79
     answers
    0.79
     revenge
    0.78
    to
    0.78
    Act Density 0.107%

    No Known Activations