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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "move."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĥ
    -1.70
    icum
    -1.50
    §
    -1.49
    ĥ½
    -1.44
    Į
    -1.43
    dere
    -1.39
    ľĵ
    -1.37
    »¿
    -1.36
     courage
    -1.36
    hedral
    -1.34
    POSITIVE LOGITS
    able
    2.38
    ability
    1.72
    legged
    1.67
    chip
    1.58
    manship
    1.50
    man
    1.47
    maker
    1.47
    thm
    1.44
    plant
    1.43
     controls
    1.43
    Act Density 0.034%

    No Known Activations