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

    Neuronpedia

    INDEX
    Explanations

    phrases associated with environmental conditions or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andowski
    -0.72
    lear
    -0.71
     Collider
    -0.70
     Ames
    -0.68
    amera
    -0.67
    arez
    -0.66
     Dhabi
    -0.65
    JM
    -0.65
     Dialogue
    -0.64
    IDA
    -0.64
    POSITIVE LOGITS
    oshenko
    0.73
     gran
    0.71
     ice
    0.69
     lin
    0.68
    owler
    0.65
     disk
    0.64
     gravel
    0.64
     pellets
    0.60
     flakes
    0.60
     minerals
    0.59
    Act Density 0.151%

    No Known Activations