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

    Neuronpedia

    INDEX
    Explanations

    the verb "to be" and its various forms in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hops
    -0.63
     ski
    -0.60
     Strawberry
    -0.58
     hurricanes
    -0.58
     SNAP
    -0.58
     Helic
    -0.57
     DRAG
    -0.57
     grandchildren
    -0.55
     Rubin
    -0.54
     Pin
    -0.54
    POSITIVE LOGITS
    inated
    0.82
    ored
    0.81
    inate
    0.80
    oured
    0.76
    culus
    0.72
    phas
    0.72
    ony
    0.72
    tre
    0.72
    ax
    0.70
    aker
    0.70
    Act Density 0.007%

    No Known Activations