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

    Neuronpedia

    INDEX
    Explanations

    instances of "over" and related prepositional or causal phrases that indicate reasons or conditions surrounding actions and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obi
    -0.77
     toget
    -0.75
    nes
    -0.73
    Registered
    -0.70
    Ear
    -0.70
    iol
    -0.69
     happiest
    -0.67
    CO
    -0.67
    CHR
    -0.65
    Sleep
    -0.65
    POSITIVE LOGITS
     allegations
    1.08
     accusations
    1.03
     violations
    1.02
     disagreements
    1.01
     violating
    1.01
     misconduct
    1.00
     mishand
    0.94
     complaints
    0.90
     irregularities
    0.90
     breaching
    0.88
    Act Density 0.149%

    No Known Activations