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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing the futility or ineffectiveness of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    doing and its effects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ſſung
    -0.81
     незавершена
    -0.81
     unſer
    -0.79
    <unused17>
    -0.77
     dieſer
    -0.77
    <unused41>
    -0.76
    <unused74>
    -0.76
    <unused20>
    -0.76
    [@BOS@]
    -0.76
    <unused14>
    -0.76
    POSITIVE LOGITS
     effects
    0.40
     effect
    0.38
     effets
    0.36
    effect
    0.35
     impact
    0.35
     करे
    0.32
     effet
    0.31
     does
    0.31
     effective
    0.31
     power
    0.30
    Act Density 0.046%

    No Known Activations