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

    Neuronpedia

    INDEX
    Explanations

    phrases about maximizing benefits or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     OnTriggerEnter
    -0.56
     createSlice
    -0.55
    UnusedPrivate
    -0.55
    bouncycastle
    -0.53
     muualla
    -0.51
     CURLOPT
    -0.50
    agonia
    -0.49
    Personensuche
    -0.49
    GrantedAuthority
    -0.47
     SwiftUI
    -0.47
    POSITIVE LOGITS
     out
    1.72
     outta
    1.25
     Out
    1.13
    Out
    1.08
    out
    1.07
     OUT
    0.97
    出
    0.97
    出了
    0.84
    OutOf
    0.77
     出
    0.76
    Act Density 0.148%

    No Known Activations