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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating progress or advancement

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating progress or movement toward a goal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esm
    -0.83
    Keys
    -0.70
    ãĥĥ
    -0.68
    contract
    -0.68
    chem
    -0.68
    prefix
    -0.68
    need
    -0.68
    vari
    -0.67
    inflamm
    -0.67
    keys
    -0.67
    POSITIVE LOGITS
     recognizing
    0.71
     paddle
    0.65
     Advance
    0.65
     realizing
    0.64
     acknowledging
    0.64
     considering
    0.63
     achievable
    0.62
     srfAttach
    0.61
     hindsight
    0.61
     disadvant
    0.58
    Act Density 0.047%

    No Known Activations